© 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. 119037
    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
    integral
    -0.07
     integral
    -0.07
     solid
    -0.07
     Integral
    -0.06
    PKG
    -0.06
    .keywords
    -0.06
     bright
    -0.06
    stro
    -0.06
     Grass
    -0.06
    BCM
    -0.06
    POSITIVE LOGITS
     utter
    0.07
     MACHINE
    0.07
    _machine
    0.06
     Transformer
    0.06
    oks
    0.06
    omor
    0.06
     Machine
    0.06
     automát
    0.06
    ouncill
    0.06
    æĥĬ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.