© 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. 125272
    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
     modest
    -0.07
    utherland
    -0.06
     âĹĦ
    -0.06
    undry
    -0.06
    elm
    -0.06
    .::
    -0.06
    .sam
    -0.06
    esters
    -0.06
    ylvania
    -0.06
    ceae
    -0.06
    POSITIVE LOGITS
    golden
    0.07
    ssql
    0.06
    ıt
    0.06
     vess
    0.06
     golden
    0.06
    umper
    0.06
    éĬ
    0.06
     Golden
    0.06
    çĦ¡
    0.06
    lg
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.