© 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. 59123
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "hat trick" and related terms 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
    utow
    -0.09
    icha
    -0.07
    olics
    -0.07
     Pazar
    -0.06
    sehen
    -0.06
    IDD
    -0.06
    388
    -0.06
    alled
    -0.06
    BY
    -0.06
    ì¦
    -0.06
    POSITIVE LOGITS
     redux
    0.07
    rek
    0.07
     completo
    0.07
    RelativeTo
    0.06
    ixin
    0.06
    uffer
    0.06
    oria
    0.06
    ensis
    0.06
    UILD
    0.06
     completa
    0.06
    Activations Density 0.009%

    No Known Activations