© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39403
    Prev
    Next
    INDEX
    Explanations

    references to the Google brand and its associated services

    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
    λλα
    -0.07
    ãģ¡ãĤĥãĤĵ
    -0.07
    nish
    -0.06
    mae
    -0.05
    urrenc
    -0.05
    ñana
    -0.05
    sek
    -0.05
    akh
    -0.05
     threshold
    -0.05
    reen
    -0.05
    POSITIVE LOGITS
    ãĤ¥
    0.08
    ertz
    0.07
    ickers
    0.07
    plex
    0.07
    ÃŃnÄĽ
    0.07
    tram
    0.07
    imus
    0.07
     incons
    0.07
    anford
    0.07
     æĺŁ
    0.07
    Activations Density 0.009%

    No Known Activations