© 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. 94041
    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
     salopes
    -0.07
    ebi
    -0.07
    ủng
    -0.07
    iore
    -0.07
     afterward
    -0.07
    rame
    -0.07
    unde
    -0.07
    ATA
    -0.07
    ziel
    -0.07
    egade
    -0.07
    POSITIVE LOGITS
    зна
    0.06
    _critical
    0.06
     him
    0.06
     apl
    0.06
    och
    0.06
     coinc
    0.06
     вÑģÑij
    0.06
    owitz
    0.06
     Clarence
    0.06
     learning
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.