© 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 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. 88593
    Prev
    Next
    INDEX
    Explanations

    references to various sports and athletic 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
    enden
    -0.09
    agues
    -0.07
    peria
    -0.07
    arious
    -0.07
    ÙĪاÙĨ
    -0.06
    óng
    -0.06
    afen
    -0.06
    xin
    -0.06
    ovah
    -0.06
    abs
    -0.06
    POSITIVE LOGITS
    awner
    0.07
     itself
    0.07
     "(\<
    0.07
    283
    0.06
    caster
    0.06
    -wide
    0.06
    ustos
    0.06
    rey
    0.06
     DERP
    0.06
    ocode
    0.05
    Activations Density 0.024%

    No Known Activations