© 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. 9-LLAMASCOPE-RES-131K
    11. 94231
    Prev
    Next
    INDEX
    Explanations

    instances of objections or dissent 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
    allet
    -0.07
    leh
    -0.06
     sublicense
    -0.06
    دث
    -0.06
    rz
    -0.06
    ove
    -0.06
    aggi
    -0.06
    اÙģظ
    -0.06
    ýn
    -0.06
    kip
    -0.06
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.09
    ably
    0.08
    /conf
    0.08
     ìĤ¬íķŃ
    0.08
    à¸Ĺาà¸Ļ
    0.07
    omers
    0.07
    401
    0.07
    ively
    0.06
    ors
    0.06
    .Execute
    0.06
    Activations Density 0.006%

    No Known Activations