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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 55518
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and challenges

    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
     Cata
    -0.08
     Interest
    -0.07
     into
    -0.07
     interest
    -0.07
    rame
    -0.07
    ãģ¸ãģ¨
    -0.07
    lek
    -0.06
     onto
    -0.06
    odge
    -0.06
    addy
    -0.06
    POSITIVE LOGITS
     being
    0.09
    being
    0.09
    pecially
    0.08
     Being
    0.07
     especially
    0.07
     Abilities
    0.07
    #'
    0.07
    kün
    0.07
     sendo
    0.06
    achuset
    0.06
    Activations Density 0.064%

    No Known Activations