© 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. 92107
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a variety of options or categories

    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
    #__
    -0.08
     fitte
    -0.07
    éĨ´
    -0.07
    #ad
    -0.07
    é¥
    -0.07
    /her
    -0.07
    ặc
    -0.06
    spath
    -0.06
     Rank
    -0.06
     Comb
    -0.06
    POSITIVE LOGITS
     possibilities
    0.07
     imaginable
    0.07
    errat
    0.07
     circumstances
    0.06
    æĥħåĨµ
    0.06
    yum
    0.06
     interests
    0.06
    маз
    0.06
    oles
    0.06
    hiba
    0.06
    Activations Density 0.025%

    No Known Activations