© 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. 39291
    Prev
    Next
    INDEX
    Explanations

    references to image sources and copyright information

    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
    .pdf
    -0.06
     dis
    -0.06
     Web
    -0.06
     tentative
    -0.06
    ointed
    -0.05
     Space
    -0.05
     optionally
    -0.05
    lier
    -0.05
    material
    -0.05
     web
    -0.05
    POSITIVE LOGITS
    irut
    0.07
    tsy
    0.07
     hrom
    0.07
    /pub
    0.07
    æŁľ
    0.07
    _CC
    0.07
    (CC
    0.07
    ehr
    0.07
    pid
    0.07
    ìĶ¨
    0.07
    Activations Density 0.008%

    No Known Activations