© 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. 76966
    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
    ekil
    -0.07
    idal
    -0.07
    encent
    -0.07
    ì¤ij
    -0.06
    ereotype
    -0.06
    ito
    -0.06
    ÑģÑĥÑĤ
    -0.06
     Noon
    -0.06
    öyle
    -0.06
     Shay
    -0.06
    POSITIVE LOGITS
     hadn
    0.07
    èŃ
    0.06
     Caldwell
    0.06
    Href
    0.06
    ampion
    0.06
    acher
    0.06
     elasticity
    0.05
     lately
    0.05
     alf
    0.05
     Sist
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.