© 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. 125771
    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
     Highway
    -0.07
    ;element
    -0.07
    /locale
    -0.06
    ạm
    -0.06
    rips
    -0.06
     âĢª
    -0.06
     ver
    -0.06
     militar
    -0.06
    ail
    -0.06
    ("$.
    -0.05
    POSITIVE LOGITS
    ICLE
    0.07
    pace
    0.07
    omy
    0.07
    ë§¥
    0.07
    ábado
    0.06
    airro
    0.06
    .opend
    0.06
    оÑĢалÑĮ
    0.06
    proper
    0.06
     allegedly
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.