© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 87058
    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
     maneuver
    -0.06
    eless
    -0.06
     saÄŁ
    -0.06
     Duel
    -0.06
    [sizeof
    -0.06
    curring
    -0.05
     ADDR
    -0.05
    imir
    -0.05
    980
    -0.05
     POSITION
    -0.05
    POSITIVE LOGITS
    iban
    0.08
    ebi
    0.07
    ilip
    0.07
    ieties
    0.07
    ģm
    0.07
    erture
    0.07
    说è¯Ŀ
    0.07
    IE
    0.07
    ÄĽj
    0.07
    itm
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.