© 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. 83269
    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
    owy
    -0.08
    ÌĨ
    -0.07
     outr
    -0.06
    ãĤ»ãĥ³
    -0.06
     defer
    -0.06
    cone
    -0.06
    ota
    -0.06
    Forgery
    -0.06
    pong
    -0.06
    ulu
    -0.06
    POSITIVE LOGITS
     saying
    0.07
     dav
    0.06
    ÙĪÙħ
    0.06
    toc
    0.06
    _helper
    0.06
    ieu
    0.06
    124
    0.06
     grandchildren
    0.06
    oller
    0.06
     pii
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.