© 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. 54322
    Prev
    Next
    INDEX
    Explanations

    references to the physical body and its experiences

    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
     folks
    -0.07
    arc
    -0.06
    atch
    -0.06
    adge
    -0.06
    ibel
    -0.06
    coe
    -0.06
     teeth
    -0.06
    ju
    -0.06
    ut
    -0.06
     Mag
    -0.06
    POSITIVE LOGITS
     bodies
    0.12
     Bodies
    0.12
     body
    0.11
    (body
    0.10
     physical
    0.10
    身ä½ĵ
    0.10
    -body
    0.10
     Body
    0.09
    .Body
    0.09
    .body
    0.09
    Activations Density 0.017%

    No Known Activations