© 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. 117913
    Prev
    Next
    INDEX
    Explanations

    references to quotations or images associated with a context

    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
    èo
    -0.09
    ãģ¯ãģļ
    -0.07
    ett
    -0.07
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.07
    .Aggressive
    -0.06
    Ñĥда
    -0.06
    vale
    -0.06
    .CustomButton
    -0.06
    esk
    -0.06
    Äįi
    -0.06
    POSITIVE LOGITS
    obuf
    0.08
    piel
    0.06
    emode
    0.06
    hq
    0.06
    zure
    0.06
    _defs
    0.06
    tep
    0.06
     publi
    0.06
     example
    0.06
    iou
    0.06
    Activations Density 0.000%

    No Known Activations