© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83894
    Prev
    Next
    INDEX
    Explanations

    references to anatomy and physiological features, particularly related to fat and muscles

    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
    raction
    -0.07
     Tits
    -0.07
    ldre
    -0.07
    vod
    -0.06
    htable
    -0.06
    ην
    -0.06
     ÙģÙĪÙĦ
    -0.06
    mania
    -0.06
    Yaw
    -0.06
     anale
    -0.06
    POSITIVE LOGITS
     adip
    0.09
     fat
    0.09
     depot
    0.07
     obesity
    0.07
    venir
    0.07
     mass
    0.07
     ob
    0.07
    SAT
    0.07
     ple
    0.07
     stores
    0.06
    Activations Density 0.005%

    No Known Activations