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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-32K
    6. 2833
    Prev
    Next
    INDEX
    Explanations

    terminology related to sports injuries and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACA
    -0.15
    Matchers
    -0.15
     atomic
    -0.14
     Security
    -0.14
    zew
    -0.14
    омеÑĢ
    -0.13
     Atomic
    -0.13
    ulur
    -0.13
    pire
    -0.13
    woke
    -0.13
    POSITIVE LOGITS
    anz
    0.15
    ?action
    0.15
    sdale
    0.14
    ä¸ĭ载次æķ°
    0.14
     Banc
    0.14
     Phelps
    0.14
     abras
    0.14
     injured
    0.14
    á»ı
    0.13
    едини
    0.13
    Activations Density 0.259%

    No Known Activations