© 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. 76293
    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
    ãĤ¤ãĥī
    -0.07
    oloj
    -0.07
    osit
    -0.07
    ald
    -0.07
    izzo
    -0.07
    abo
    -0.07
    UTTON
    -0.07
     chá»Ĺ
    -0.07
    imd
    -0.07
    trak
    -0.07
    POSITIVE LOGITS
     couples
    0.09
     Couples
    0.08
     couple
    0.08
     Couple
    0.07
     divorce
    0.07
     marital
    0.07
     marriage
    0.07
    519
    0.07
     mutual
    0.07
    å½¼
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.