© 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. 55161
    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
    usch
    -0.07
    ohl
    -0.07
    retty
    -0.07
    ibr
    -0.06
    ÙıÙĩ
    -0.06
    abled
    -0.06
    pbs
    -0.06
    lest
    -0.06
    /lists
    -0.06
    aight
    -0.06
    POSITIVE LOGITS
    =in
    0.06
     Sweep
    0.06
    IALOG
    0.06
    RYPT
    0.06
    atown
    0.06
    çĶ
    0.06
    é»
    0.06
    enderit
    0.06
    ytt
    0.06
    NotAllowed
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.