© 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. 54262
    Prev
    Next
    INDEX
    Explanations

    references to skateboarding and related activities

    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
    liqu
    -0.07
    lies
    -0.07
    ext
    -0.07
    essor
    -0.07
    érc
    -0.06
    kker
    -0.06
    zers
    -0.06
    ional
    -0.06
    inho
    -0.06
    ãģĦãĤĭ
    -0.06
    POSITIVE LOGITS
    etched
    0.09
    boarding
    0.08
    oro
    0.08
    tember
    0.07
    ampus
    0.07
    peare
    0.07
    odom
    0.07
    ulpt
    0.07
    ETCH
    0.07
    ا
    0.07
    Activations Density 0.020%

    No Known Activations