© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 73462
    Prev
    Next
    INDEX
    Explanations

    expressions related to the benefits of exercise

    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
    steen
    -0.08
    ÑĨен
    -0.07
    ylon
    -0.07
    enas
    -0.07
    evi
    -0.07
    eid
    -0.06
    vvm
    -0.06
     corners
    -0.06
    emain
    -0.06
    oux
    -0.06
    POSITIVE LOGITS
     tread
    0.07
    endor
    0.07
    .jquery
    0.07
    ÃŃch
    0.07
    runner
    0.07
    _FETCH
    0.06
    ì§Ģê³ł
    0.06
     mood
    0.06
    cdecl
    0.06
    disposing
    0.06
    Activations Density 0.002%

    No Known Activations