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. 22-LLAMASCOPE-RES-131K
    6. 5606
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ately
    -0.07
    arine
    -0.07
    lÃŃÄį
    -0.06
    156
    -0.06
    agher
    -0.06
    //{{
    -0.06
    ej
    -0.06
    edException
    -0.06
    oze
    -0.06
    onces
    -0.06
    POSITIVE LOGITS
    rew
    0.07
    doi
    0.07
    ort
    0.07
    ook
    0.07
    ford
    0.07
    ublic
    0.07
    ew
    0.07
    udio
    0.06
    rent
    0.06
    .infinity
    0.06
    Activations Density 0.002%

    No Known Activations