© 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. 89506
    Prev
    Next
    INDEX
    Explanations

    details about financial compensations, specifically related to pensions

    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
    iment
    -0.07
    fern
    -0.07
     dash
    -0.06
    rous
    -0.06
    ouden
    -0.06
    mür
    -0.06
    .asc
    -0.06
    agen
    -0.06
    dash
    -0.06
    958
    -0.06
    POSITIVE LOGITS
    ÙĪد
    0.07
    å¥
    0.07
    chemas
    0.06
    ведиÑĤе
    0.06
    ossal
    0.06
    ntl
    0.06
    .getProperties
    0.06
     Pret
    0.06
     pun
    0.06
     Sands
    0.06
    Activations Density 0.010%

    No Known Activations