© 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. 2403
    Prev
    Next
    INDEX
    Explanations

    combinations of ingredients or items presented in a list-like format

    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
    cher
    -0.07
    ightly
    -0.07
    andin
    -0.07
    )((((
    -0.07
    ãĥ¼ãĤ¸
    -0.07
    ãĥ¼ãĥĸãĥ«
    -0.07
    oj
    -0.07
    opot
    -0.06
    ->{$
    -0.06
    none
    -0.06
    POSITIVE LOGITS
    /or
    0.10
    /of
    0.09
    /OR
    0.08
     _______,
    0.07
    á»Ļt
    0.07
     either
    0.06
    [of
    0.06
    amping
    0.06
     Cler
    0.06
    ört
    0.06
    Activations Density 0.065%

    No Known Activations