© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126050
    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
    elden
    -0.08
    antas
    -0.07
    irie
    -0.07
     sede
    -0.07
    duk
    -0.07
     çŃ
    -0.07
    lak
    -0.07
    rych
    -0.07
    eld
    -0.07
    plode
    -0.07
    POSITIVE LOGITS
     nomin
    0.06
     lith
    0.06
     Harden
    0.06
     Europe
    0.06
    181
    0.06
     again
    0.06
     â
    0.05
     prest
    0.05
    331
    0.05
     dime
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.