© 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. 82601
    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
    riot
    -0.07
    276
    -0.06
    FSIZE
    -0.06
     -:-
    -0.06
     Evel
    -0.06
     Sar
    -0.06
     turno
    -0.06
     panel
    -0.05
     |[
    -0.05
    PTS
    -0.05
    POSITIVE LOGITS
     fuck
    0.08
     fucked
    0.07
     FUCK
    0.07
     Fuck
    0.07
    ssf
    0.07
    .wind
    0.07
     fucking
    0.07
    nodoc
    0.07
    Fuck
    0.07
    WF
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.