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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 12-LLAMASCOPE-RES-32K
    6. 32061
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÐĺТ
    -0.14
    forma
    -0.14
    ìĹ´
    -0.14
    peri
    -0.13
    ÑĩиÑģл
    -0.13
     æĮ
    -0.13
     Vill
    -0.13
    agr
    -0.13
    upa
    -0.12
    gly
    -0.12
    POSITIVE LOGITS
    achs
    0.18
    ึà¸ĩ
    0.16
     Towers
    0.15
    ãĥĢãĤ¤
    0.15
     Kunst
    0.15
    imir
    0.14
     Giles
    0.14
    pel
    0.14
    udios
    0.14
    imit
    0.14
    Activations Density 0.017%

    No Known Activations