© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 20062
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terminology, particularly related to systems and structural components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words containing the letter sequence "s" followed by a vowel, particularly in names and technical terms (like "Sac", "sar", "Ser", "SB").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éis
    -0.18
    ãģĬãĤĬ
    -0.16
    cre
    -0.16
    uar
    -0.15
    printer
    -0.15
    .middleware
    -0.15
    loan
    -0.15
    usc
    -0.15
    ritz
    -0.15
    ubern
    -0.15
    POSITIVE LOGITS
    isbury
    0.21
    urai
    0.20
    vation
    0.19
    tember
    0.18
    chez
    0.18
    ellite
    0.18
    bastian
    0.17
    posium
    0.17
    -स
    0.16
    iego
    0.16
    Activations Density 3.540%

    No Known Activations