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 (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44136
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignet
    -0.07
    ancer
    -0.07
    antage
    -0.07
    eus
    -0.07
    .same
    -0.07
    avax
    -0.07
    umsuz
    -0.07
    ustom
    -0.06
    PackageName
    -0.06
    outines
    -0.06
    POSITIVE LOGITS
     Jeg
    0.09
     Meg
    0.09
     Mag
    0.08
     Arch
    0.08
     Ford
    0.08
    Meg
    0.08
     arch
    0.07
     ford
    0.07
    (ang
    0.07
     Lap
    0.07
    Activations Density 0.004%

    No Known Activations