© 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. 129118
    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
     Ferr
    -0.07
     çĬ
    -0.06
    é¨İ
    -0.06
    gnore
    -0.06
    çĮ
    -0.06
    iad
    -0.06
    ÑĥлÑĮ
    -0.06
    475
    -0.06
    chw
    -0.06
    ÃĦ
    -0.06
    POSITIVE LOGITS
     clan
    0.08
     Indigenous
    0.07
     tribal
    0.07
     Native
    0.07
    ewis
    0.07
     Clan
    0.07
    hlen
    0.07
    ikip
    0.07
    .Native
    0.07
    DDR
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.