© 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. 104690
    Prev
    Next
    INDEX
    Explanations

    references to serialized objects in code documentation

    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
    elpers
    -0.08
    ieber
    -0.07
    >NN
    -0.07
    activex
    -0.07
    ters
    -0.07
    wo
    -0.07
    оваÑĢ
    -0.07
    lotte
    -0.06
    stdlib
    -0.06
    pson
    -0.06
    POSITIVE LOGITS
     cref
    0.09
    ://
    0.07
    uin
    0.06
    erness
    0.06
    chod
    0.06
     rough
    0.06
     Rough
    0.06
    άÏĥ
    0.06
    _tac
    0.06
    557
    0.06
    Activations Density 0.003%

    No Known Activations