© 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. 60662
    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
     Kraj
    -0.06
    emma
    -0.06
    bdd
    -0.06
    Dot
    -0.06
    ض
    -0.06
     IDb
    -0.06
    ece
    -0.05
    ODO
    -0.05
     Pace
    -0.05
     Wet
    -0.05
    POSITIVE LOGITS
    inho
    0.09
    rug
    0.07
     everybody
    0.07
    afil
    0.07
    aux
    0.07
    assin
    0.06
    оÑĢÑĥ
    0.06
     Rodrig
    0.06
    -ÑĤо
    0.06
    ibaba
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.