© 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. 58309
    Prev
    Next
    INDEX
    Explanations

    references to the number of outs in a baseball game

    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
    μεν
    -0.08
    ذا
    -0.07
    isku
    -0.07
    ENER
    -0.07
    ystack
    -0.07
    atron
    -0.07
    idla
    -0.07
    enin
    -0.06
    /topics
    -0.06
    STACK
    -0.06
    POSITIVE LOGITS
    esses
    0.06
    sts
    0.06
     desper
    0.06
    yd
    0.06
    yu
    0.06
    agues
    0.06
     ÑĢеж
    0.06
    bie
    0.06
    anger
    0.06
    portun
    0.06
    Activations Density 0.001%

    No Known Activations