© 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. 108687
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and concepts

    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
     Slip
    -0.07
    ppe
    -0.06
    xxxxxxxx
    -0.06
    tec
    -0.06
    unn
    -0.06
    prite
    -0.06
     Umb
    -0.06
    çµ
    -0.06
    etwork
    -0.06
    iesz
    -0.06
    POSITIVE LOGITS
    /latest
    0.07
     applicable
    0.07
    laws
    0.07
    одав
    0.07
    iÄĩ
    0.06
    _gap
    0.06
    appen
    0.06
    æľºåħ³
    0.06
    ethoven
    0.06
    ved
    0.06
    Activations Density 0.009%

    No Known Activations