© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77571
    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
    missions
    -0.07
    elu
    -0.07
     clo
    -0.07
    angible
    -0.07
    åĽ´
    -0.07
    hesive
    -0.07
    rosso
    -0.06
    olk
    -0.06
    пÑĢ
    -0.06
    adors
    -0.06
    POSITIVE LOGITS
     Minimal
    0.07
    ÅĪ
    0.07
    lices
    0.06
    eor
    0.06
     #-
    0.06
    SHIFT
    0.06
    Minimal
    0.06
     strains
    0.06
     gratuites
    0.06
    ocker
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.