© 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. 84148
    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
     advance
    -0.06
     postings
    -0.06
    phia
    -0.06
    ocate
    -0.06
    书记
    -0.06
    _PARAMETERS
    -0.06
     sez
    -0.06
     IReadOnly
    -0.06
     aria
    -0.06
    iban
    -0.06
    POSITIVE LOGITS
    warts
    0.07
    pies
    0.06
    uki
    0.06
     Mahmoud
    0.06
    åįĵ
    0.06
    wright
    0.06
    ighth
    0.06
    YouTube
    0.06
    usercontent
    0.06
    HTTPS
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.