© 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. 55970
    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
     Brotherhood
    -0.07
    á»ĭ
    -0.07
    _RTC
    -0.06
    Ìī
    -0.06
    kses
    -0.06
    پس
    -0.06
     پس
    -0.06
    iew
    -0.06
    rive
    -0.06
    /pg
    -0.06
    POSITIVE LOGITS
     Nin
    0.07
    504
    0.06
     buffering
    0.06
    éĹľ
    0.06
    -lnd
    0.05
     now
    0.05
    vana
    0.05
    авиÑģ
    0.05
    ATUS
    0.05
     Leone
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.