© 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. 124463
    Prev
    Next
    INDEX
    Explanations

    elements related to physical sensations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     overload
    -0.06
    -0.06
    let
    -0.06
     everywhere
    -0.06
     good
    -0.06
    yr
    -0.06
    .sdk
    -0.06
    rest
    -0.05
     Road
    -0.05
     widespread
    -0.05
    POSITIVE LOGITS
    pgsql
    0.08
    onu
    0.08
    olla
    0.08
    endar
    0.07
    .scalablytyped
    0.07
     uncomment
    0.07
     èĩªåĬ¨çĶŁæĪIJ
    0.07
    ENDOR
    0.07
    ÙĪÙĨا
    0.07
    STALL
    0.07
    Activations Density 0.007%

    No Known Activations