© 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. 16651
    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
    á»ĩ
    -0.07
    ë°©
    -0.07
    actionDate
    -0.07
    rib
    -0.07
     WARRANT
    -0.07
    reck
    -0.06
    prot
    -0.06
    erti
    -0.06
    rax
    -0.06
    ë¡Ń
    -0.06
    POSITIVE LOGITS
    otten
    0.07
     nat
    0.07
    æħ¶
    0.06
    ITICAL
    0.06
     Nat
    0.06
    γκε
    0.06
     hed
    0.06
    cached
    0.06
    isen
    0.06
    osoph
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.