© 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. 18477
    Prev
    Next
    INDEX
    Explanations

    the phrase "in the middle" and similar expressions indicating centrality or location

    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
    ouv
    -0.07
     McGregor
    -0.07
    gmt
    -0.07
    eric
    -0.07
    zcze
    -0.07
    _mgmt
    -0.06
    antu
    -0.06
    над
    -0.06
    dG
    -0.06
    оба
    -0.06
    POSITIVE LOGITS
    uges
    0.07
    punkt
    0.07
     nowhere
    0.07
    vous
    0.07
    veis
    0.06
    -middle
    0.06
    sticks
    0.06
    .heroku
    0.06
    ather
    0.06
    flen
    0.06
    Activations Density 0.005%

    No Known Activations