© 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. 88021
    Prev
    Next
    INDEX
    Explanations

    references to draft picks in sports contexts

    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
    zap
    -0.07
    cheng
    -0.07
    stoff
    -0.06
    žit
    -0.06
    eyse
    -0.06
    FALSE
    -0.06
    ington
    -0.06
    pte
    -0.06
     Ziel
    -0.06
    avascript
    -0.06
    POSITIVE LOGITS
    ì§ľ
    0.08
    ers
    0.08
    yal
    0.07
    ships
    0.07
     createAction
    0.06
    pers
    0.06
    InSection
    0.06
    ÑĪ
    0.06
     proven
    0.06
    gh
    0.06
    Activations Density 0.002%

    No Known Activations