© 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. 117336
    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
     sez
    -0.07
    280
    -0.07
    jal
    -0.07
     wrench
    -0.06
    çĽ
    -0.06
    amas
    -0.06
    _PHYS
    -0.06
    iya
    -0.06
     memorial
    -0.06
    Ø°
    -0.05
    POSITIVE LOGITS
    hton
    0.07
    pto
    0.07
    nr
    0.07
     hereby
    0.07
     lekker
    0.06
    uito
    0.06
    .PropTypes
    0.06
    bjerg
    0.06
    inspace
    0.06
    phies
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.