© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60684
    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
     ::
    -0.07
     natural
    -0.06
    EFA
    -0.06
    itations
    -0.06
    oy
    -0.06
    ãģķãĤī
    -0.06
    agina
    -0.06
    ãĥ¬ãĥ³
    -0.06
    asons
    -0.06
    Warnings
    -0.06
    POSITIVE LOGITS
     Sle
    0.07
    stuff
    0.07
     Gür
    0.07
    jee
    0.06
    chl
    0.06
    essional
    0.06
    middlewares
    0.06
    огод
    0.06
    statt
    0.06
     blobs
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.