© 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. 9-LLAMASCOPE-RES-131K
    11. 98652
    Prev
    Next
    INDEX
    Explanations

    identifiers related to tracking and analytics

    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
    positor
    -0.07
    ynth
    -0.07
    isser
    -0.06
    fuse
    -0.06
    yn
    -0.06
    Ñıд
    -0.06
    engkap
    -0.06
     Patterson
    -0.06
     Fuse
    -0.06
     лок
    -0.06
    POSITIVE LOGITS
    611
    0.06
    dee
    0.06
    æĿ
    0.06
    롱
    0.06
    arn
    0.06
    rophy
    0.06
    bled
    0.06
    _Destroy
    0.06
    _ENABLED
    0.05
    ngr
    0.05
    Activations Density 0.001%

    No Known Activations