© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88621
    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
    ych
    -0.08
    åķ
    -0.07
    omo
    -0.07
    oden
    -0.06
    avor
    -0.06
    apl
    -0.06
    елен
    -0.06
    ä»ĭ
    -0.06
    quina
    -0.06
    781
    -0.06
    POSITIVE LOGITS
    mith
    0.08
    Entr
    0.07
    ngrx
    0.06
     anytime
    0.06
    ÑĢол
    0.06
    \param
    0.06
     XPAR
    0.06
    entr
    0.06
    gebra
    0.06
    feof
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.