© 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. 9-LLAMASCOPE-RES-131K
    11. 94939
    Prev
    Next
    INDEX
    Explanations

    terms related to lifestyle and fashion

    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
    ìĦ¸
    -0.07
    ysz
    -0.06
    åıªèĥ½
    -0.06
    utz
    -0.06
    mae
    -0.06
    -powered
    -0.06
     thr
    -0.06
    miss
    -0.06
    utions
    -0.06
    ETA
    -0.06
    POSITIVE LOGITS
    .camel
    0.07
    tainment
    0.07
    getti
    0.07
    alu
    0.07
    RICT
    0.07
    getReference
    0.07
    à¥įà¤
    0.07
    lement
    0.07
    .ot
    0.06
    IFS
    0.06
    Activations Density 0.003%

    No Known Activations