© 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. 40081
    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
     consc
    -0.06
    orden
    -0.06
     mag
    -0.06
     kicking
    -0.06
     sacr
    -0.06
    lius
    -0.06
    .dtype
    -0.06
    ç½®
    -0.05
     Kaiser
    -0.05
    iasm
    -0.05
    POSITIVE LOGITS
    iren
    0.08
    luet
    0.07
    @brief
    0.07
    iscal
    0.07
    pn
    0.07
    illas
    0.07
     Socorro
    0.07
    -Ta
    0.06
    .tc
    0.06
    (æĹ¥
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.