© 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. 5805
    Prev
    Next
    INDEX
    Explanations

    parentheses and related numerical or measurement information

    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
    ultz
    -0.07
    anders
    -0.06
    iÄįe
    -0.06
     sposób
    -0.06
     ranges
    -0.06
    ÅĻil
    -0.06
     дÑĥÑħ
    -0.06
    defgroup
    -0.06
     heightFor
    -0.06
    ISTR
    -0.06
    POSITIVE LOGITS
    nez
    0.06
     NÄĽm
    0.06
     Haz
    0.06
     compared
    0.06
    oned
    0.06
    igu
    0.06
    pn
    0.05
    uese
    0.05
    ramer
    0.05
     Lap
    0.05
    Activations Density 0.002%

    No Known Activations