© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118591
    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
     ActionTypes
    -0.06
    inand
    -0.06
    pond
    -0.06
    erset
    -0.06
     Salisbury
    -0.06
    orado
    -0.06
    yor
    -0.06
    erton
    -0.05
    rels
    -0.05
    eer
    -0.05
    POSITIVE LOGITS
    ixmap
    0.07
    linkplain
    0.07
    ikat
    0.07
    Localized
    0.07
    Ñĥва
    0.07
    ISIBLE
    0.06
     Fuck
    0.06
    ointment
    0.06
    usi
    0.06
    å¾Ĵ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.