© 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. 80886
    Prev
    Next
    INDEX
    Explanations

    concepts related to values and ethics

    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
    enson
    -0.07
    akis
    -0.07
     abl
    -0.06
     ãĤĤ
    -0.06
    ierge
    -0.06
    agos
    -0.06
     worsh
    -0.06
    773
    -0.06
    aland
    -0.06
    onen
    -0.06
    POSITIVE LOGITS
    myModal
    0.07
    vant
    0.07
    ktop
    0.06
    اء
    0.06
    touches
    0.06
    üc
    0.06
    ẫ
    0.06
    plements
    0.06
    npj
    0.06
    iates
    0.06
    Activations Density 0.002%

    No Known Activations