© 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. 55841
    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
    peria
    -0.07
     @
    -0.06
    ette
    -0.06
    ANGO
    -0.06
    geme
    -0.06
     trough
    -0.06
    erna
    -0.06
     /
    -0.05
    ango
    -0.05
     neces
    -0.05
    POSITIVE LOGITS
     Wich
    0.09
    spm
    0.07
    ummies
    0.07
    687
    0.06
     Guth
    0.06
     randomly
    0.06
     оÑĤп
    0.06
    ®
    0.06
     {\↵
    0.06
     lawmaker
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.