© 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. 39672
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking methods, particularly related to recipes

    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
    odore
    -0.10
    ÑįÑĤомÑĥ
    -0.09
    opi
    -0.07
    Injector
    -0.07
    unto
    -0.07
    obox
    -0.07
    bsites
    -0.07
    alore
    -0.06
    ajs
    -0.06
    etheless
    -0.06
    POSITIVE LOGITS
     Bol
    0.07
    elez
    0.06
    õ
    0.06
     noqa
    0.06
     Gol
    0.06
    ¯
    0.05
     disp
    0.05
    eler
    0.05
    оÑĤов
    0.05
     funny
    0.05
    Activations Density 0.028%

    No Known Activations