© 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 EvalsExportsinterp-engineNEWAPI 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. 124749
    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
     Safe
    -0.06
    alarm
    -0.06
     safe
    -0.05
    adh
    -0.05
    zahl
    -0.05
    anik
    -0.05
     Records
    -0.05
    ç·ł
    -0.05
     unc
    -0.05
     Dw
    -0.05
    POSITIVE LOGITS
    aben
    0.07
    osal
    0.07
    绾
    0.07
    çģŃ
    0.07
    elta
    0.07
    ibel
    0.07
    ElementsBy
    0.07
    ози
    0.07
    loomberg
    0.07
    CONTEXT
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.