© 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. 70425
    Prev
    Next
    INDEX
    Explanations

    references to tags and categories in the context of articles

    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
    bpp
    -0.07
    arda
    -0.07
    UCCEEDED
    -0.06
     crossword
    -0.06
    imei
    -0.06
    Ñĥков
    -0.06
    же
    -0.06
    azen
    -0.06
    ursed
    -0.06
    lbrace
    -0.06
    POSITIVE LOGITS
     tag
    0.08
     tagged
    0.07
    oppins
    0.07
     Pang
    0.07
    OOD
    0.07
    tags
    0.07
    ocre
    0.06
    OPT
    0.06
    ãģĭãģª
    0.06
     Alv
    0.06
    Activations Density 0.002%

    No Known Activations