© 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. 86577
    Prev
    Next
    INDEX
    Explanations

    references to various forms of research and academic study

    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
    zon
    -0.09
    stones
    -0.08
    loe
    -0.07
    anders
    -0.07
    erea
    -0.07
    standing
    -0.07
    uro
    -0.07
    /out
    -0.07
    asc
    -0.07
    /bus
    -0.07
    POSITIVE LOGITS
    ogue
    0.07
    blr
    0.07
     abroad
    0.07
    tro
    0.07
    cation
    0.07
    PFN
    0.07
    گراÙĨ
    0.07
    elling
    0.06
    iare
    0.06
    rys
    0.06
    Activations Density 0.046%

    No Known Activations