Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 119248
    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
    ENA
    -0.07
    ض
    -0.07
    Ậ
    -0.07
    ضاÙĨ
    -0.07
    ï¸
    -0.07
    OLON
    -0.07
    çķ¥
    -0.07
    .nodeType
    -0.07
     richtig
    -0.07
     apiUrl
    -0.07
    POSITIVE LOGITS
     matter
    0.07
    elia
    0.06
     paved
    0.06
    ombre
    0.06
    림
    0.06
    IRMWARE
    0.05
     ax
    0.05
     Forums
    0.05
    iner
    0.05
    cape
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.