© 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. 116355
    Prev
    Next
    INDEX
    Explanations

    character descriptions and relationships in narratives

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    cak
    -0.08
    _COMPAT
    -0.07
    raphics
    -0.07
    vore
    -0.07
    rieb
    -0.07
    оваÑĢ
    -0.07
    ypes
    -0.07
    combe
    -0.06
    ADF
    -0.06
    lub
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸Ģ个
    0.07
     titular
    0.06
    ensitive
    0.06
     protagonist
    0.06
     protagon
    0.06
     reluctantly
    0.06
    reamble
    0.06
     ÙĨØ®
    0.06
    _prompt
    0.06
     age
    0.06
    Activations Density 0.026%

    No Known Activations