© 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. 95998
    Prev
    Next
    INDEX
    Explanations

    references to self-directed or do-it-yourself (DIY) activities

    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
    actionDate
    -0.07
    uma
    -0.07
    arty
    -0.07
    ÄĽnÃŃ
    -0.07
    agos
    -0.07
    воÑİ
    -0.07
    ãĥ¼ãĥĨãĤ£
    -0.06
    stp
    -0.06
    æ®
    -0.06
    hid
    -0.06
    POSITIVE LOGITS
    /self
    0.10
     Self
    0.07
    Self
    0.07
     style
    0.07
    ç«ĭãģ¦
    0.07
     self
    0.07
    self
    0.07
    -style
    0.06
    bie
    0.06
    éĹ
    0.06
    Activations Density 0.009%

    No Known Activations