© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 12379
    Prev
    Next
    INDEX
    Explanations

    technical or programming-related terminology and formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ainers
    -0.16
    иÑĤелÑĮноÑģÑĤÑĮ
    -0.15
    ish
    -0.14
    ierung
    -0.14
     Mann
    -0.14
    dish
    -0.14
     Copp
    -0.14
    оÑĢа
    -0.14
    haust
    -0.14
    عÙĬ
    -0.14
    POSITIVE LOGITS
    ãĥ³ãĥĢ
    0.17
     Randall
    0.15
    phin
    0.15
    Flat
    0.15
     Flat
    0.14
    flat
    0.14
     grátis
    0.14
     rodin
    0.14
    877
    0.14
    entin
    0.14
    Activations Density 0.005%

    No Known Activations