© 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. 54037
    Prev
    Next
    INDEX
    Explanations

    actions and commitments related to responsibility and reliability

    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
    azo
    -0.08
    273
    -0.07
    eselect
    -0.07
    iếp
    -0.07
    بÙĪÙĦ
    -0.07
    OAD
    -0.07
    iá»ĥn
    -0.07
    ÃŃrk
    -0.07
    TestMethod
    -0.07
    .Bunifu
    -0.07
    POSITIVE LOGITS
     promise
    0.24
     promises
    0.23
     promised
    0.22
     Promise
    0.20
    Promise
    0.17
    promise
    0.16
     promising
    0.14
    .promise
    0.11
    .Promise
    0.11
     pledged
    0.11
    Activations Density 0.031%

    No Known Activations