Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 23-LLAMASCOPE-RES-32K
    6. 723
    Prev
    Next
    INDEX
    Explanations

    attributes related to web page formatting and structured data

    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
    .bz
    -0.15
    uu
    -0.15
     Graves
    -0.14
    à¥ģब
    -0.14
    .mit
    -0.14
    rium
    -0.14
    .prototype
    -0.14
    furt
    -0.14
    fruit
    -0.14
    vos
    -0.14
    POSITIVE LOGITS
     mast
    0.18
    arty
    0.17
     Mast
    0.15
     gh
    0.14
    anta
    0.14
    ç¶
    0.14
    iday
    0.14
    mast
    0.14
    rene
    0.14
    ool
    0.14
    Activations Density 0.010%

    No Known Activations