© 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. 15-LLAMASCOPE-RES-131K
    11. 85993
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of general interest or investment

    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
    ricanes
    -0.08
    iç
    -0.07
    iddi
    -0.07
    ãģ«ãģ¤
    -0.07
    agnostics
    -0.07
    meyi
    -0.07
    achuset
    -0.07
     Roth
    -0.06
    uchos
    -0.06
    /icons
    -0.06
    POSITIVE LOGITS
     necessarily
    0.07
    NONE
    0.07
    erg
    0.07
     other
    0.06
     except
    0.06
     us
    0.06
    things
    0.06
     neither
    0.06
     nor
    0.06
     bat
    0.06
    Activations Density 0.008%

    No Known Activations