© 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. 87315
    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
     fucking
    -0.06
    ollo
    -0.06
     inc
    -0.06
    postalcode
    -0.06
     -
    -0.06
     gonna
    -0.06
    äºĭ
    -0.06
    ivan
    -0.06
    acier
    -0.06
     ‘
    -0.06
    POSITIVE LOGITS
    fragistics
    0.08
    PÅĻi
    0.07
    @Resource
    0.07
    sizei
    0.07
    Když
    0.07
    ecd
    0.07
    apos
    0.06
    REFERENCES
    0.06
    zÄħd
    0.06
    \Bundle
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.