© 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. 17374
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or help

    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
    lew
    -0.07
    ombat
    -0.07
    osten
    -0.06
     *__
    -0.06
    eno
    -0.06
    ivol
    -0.06
    è©ŀ
    -0.06
    apol
    -0.06
    regor
    -0.06
    illet
    -0.06
    POSITIVE LOGITS
     suggestions
    0.07
     help
    0.07
     помоÑī
    0.07
    erer
    0.07
     Hilfe
    0.06
    HELP
    0.06
    help
    0.06
     vui
    0.06
     aid
    0.06
     consc
    0.06
    Activations Density 0.005%

    No Known Activations