© 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. 80568
    Prev
    Next
    INDEX
    Explanations

    geographic locations and their connections

    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
    libc
    -0.07
    oba
    -0.07
     highways
    -0.06
    ultz
    -0.06
     seedu
    -0.06
    isté
    -0.06
    upal
    -0.06
    oten
    -0.06
    osy
    -0.06
    orry
    -0.06
    POSITIVE LOGITS
     station
    0.13
     stations
    0.13
     Stations
    0.12
     Station
    0.11
    é§ħ
    0.11
    station
    0.09
     train
    0.09
     terminal
    0.09
    _station
    0.09
    Station
    0.09
    Activations Density 0.010%

    No Known Activations