© 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. 54005
    Prev
    Next
    INDEX
    Explanations

    mentions of fundraising and charitable contributions

    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
    bose
    -0.07
    åľ¨çº¿éĺħ读
    -0.07
    vÄĽt
    -0.07
     MILF
    -0.07
    zel
    -0.07
     kak
    -0.07
    plex
    -0.06
    ÏĥÏĦα
    -0.06
     Τι
    -0.06
    ECTOR
    -0.06
    POSITIVE LOGITS
     charities
    0.08
     scholarships
    0.08
     local
    0.07
     future
    0.07
     fund
    0.07
     Initi
    0.07
     causes
    0.07
    ichert
    0.07
    raise
    0.07
     initiatives
    0.07
    Activations Density 0.018%

    No Known Activations