© 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. 120761
    Prev
    Next
    INDEX
    Explanations

    references to athletes or players in various 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
    kees
    -0.08
    ensi
    -0.08
    aries
    -0.08
    gers
    -0.08
    erty
    -0.08
    ens
    -0.07
    uto
    -0.07
    AY
    -0.07
    uous
    -0.07
    ral
    -0.07
    POSITIVE LOGITS
    hips
    0.11
    innen
    0.10
    hood
    0.10
    house
    0.07
    hip
    0.07
    gebn
    0.07
    stuff
    0.07
    åĢij
    0.07
    IFF
    0.06
    hattan
    0.06
    Activations Density 0.026%

    No Known Activations