© 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. 74768
    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
    olia
    -0.06
    .rt
    -0.06
    arendra
    -0.06
    atz
    -0.06
    ansk
    -0.06
    egas
    -0.06
    .assignment
    -0.06
     Holocaust
    -0.06
     informations
    -0.06
    perature
    -0.06
    POSITIVE LOGITS
     our
    0.07
     ours
    0.07
    nÃŃ
    0.07
    RICT
    0.07
    ernet
    0.06
    åŁİ
    0.06
     village
    0.06
     rains
    0.06
    our
    0.06
     locally
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.