© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31446
    Prev
    Next
    INDEX
    Explanations

    physical interactions or gestures

    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
    å½¹
    -0.07
    redient
    -0.06
    imizer
    -0.06
    بØŃ
    -0.06
    ABCDEFG
    -0.06
    ÑĢиÑĩ
    -0.06
    esch
    -0.06
    ä¼
    -0.06
    æ¡Ī
    -0.06
    RequestBody
    -0.06
    POSITIVE LOGITS
     mouth
    0.09
     miá»ĩng
    0.08
    umblr
    0.08
    -mouth
    0.07
     Mouth
    0.07
     mouths
    0.07
     lips
    0.07
     ìŀħ
    0.07
    é¡į
    0.07
     ear
    0.07
    Activations Density 0.009%

    No Known Activations