© 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. 42594
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "toggle" in various contexts

    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
    enant
    -0.07
     Pell
    -0.07
    omers
    -0.06
    ecided
    -0.06
    ople
    -0.06
    ollapse
    -0.06
    nie
    -0.06
    shed
    -0.06
    tras
    -0.06
    lassian
    -0.06
    POSITIVE LOGITS
     RedirectTo
    0.07
     ÙĨÚ¯
    0.07
    /export
    0.07
    ÑĢиÑĦ
    0.06
    _rng
    0.06
    %=
    0.06
    .EXP
    0.06
    ÑĪин
    0.06
    ayi
    0.06
    åĬ¨çĶŁæĪIJ
    0.06
    Activations Density 0.001%

    No Known Activations