© 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. 89124
    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
    евÑĸ
    -0.07
     contingency
    -0.06
    lesh
    -0.06
    ense
    -0.06
    ampa
    -0.06
    aval
    -0.06
    KM
    -0.06
    quarters
    -0.06
    èĵ
    -0.06
    olumn
    -0.06
    POSITIVE LOGITS
    ewire
    0.08
    ead
    0.07
    erokee
    0.07
    edriver
    0.07
    etype
    0.07
    setParameter
    0.07
    OAD
    0.07
    egr
    0.06
    imon
    0.06
    mars
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.