© 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. 87682
    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
    kart
    -0.06
     
    -0.06
     unique
    -0.06
     Jarvis
    -0.06
    aters
    -0.06
     pap
    -0.06
     Artifact
    -0.05
     ember
    -0.05
     Ultr
    -0.05
     options
    -0.05
    POSITIVE LOGITS
    anean
    0.08
    оналÑĮ
    0.07
    æ°ı
    0.07
    uttle
    0.07
     circulated
    0.07
     discipl
    0.07
    ãĥģãĥ¥
    0.07
    ÑĪиб
    0.07
    urovision
    0.07
    .ci
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.