© 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. 92355
    Prev
    Next
    INDEX
    Explanations

    classes and methods related to testing frameworks in programming

    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
    [thread
    -0.07
    /provider
    -0.06
    ToBounds
    -0.06
    ty
    -0.06
     ÙħØ«
    -0.06
    enti
    -0.06
    cock
    -0.06
    ?type
    -0.06
    530
    -0.06
    ISIBLE
    -0.06
    POSITIVE LOGITS
    ighting
    0.06
    ndo
    0.06
    crap
    0.06
    orie
    0.06
    igham
    0.06
    etest
    0.06
    онаÑħ
    0.05
    uben
    0.05
    ãĤ¹ãĥĨãĤ£
    0.05
    oland
    0.05
    Activations Density 0.000%

    No Known Activations