© 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. 15-LLAMASCOPE-RES-131K
    11. 86204
    Prev
    Next
    INDEX
    Explanations

    geographical locations and cities mentioned in the text

    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
     Hlav
    -0.07
    less
    -0.07
    erer
    -0.07
    inu
    -0.07
    tere
    -0.06
    evin
    -0.06
    pret
    -0.06
    LIC
    -0.06
    kie
    -0.06
     VÅ¡
    -0.06
    POSITIVE LOGITS
    anness
    0.09
    ensis
    0.09
     Pty
    0.07
     Cumhuriyeti
    0.07
    enses
    0.07
    /local
    0.07
    /blue
    0.07
    plode
    0.07
    shire
    0.07
    gov
    0.06
    Activations Density 0.049%

    No Known Activations