© 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. 22-LLAMASCOPE-RES-131K
    11. 4210
    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
    enny
    -0.06
    897
    -0.06
    ÃŁe
    -0.06
    о
    -0.06
    aload
    -0.06
    ,},↵
    -0.06
    raison
    -0.06
    .tk
    -0.06
    indows
    -0.06
    ocre
    -0.05
    POSITIVE LOGITS
    /+
    0.08
    Fax
    0.07
    ÑģÑĮого
    0.07
    Τα
    0.07
    ecko
    0.07
     Marino
    0.07
    CallCheck
    0.07
    åij¼
    0.07
    _Tis
    0.06
    رسÛĮ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.