© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3589
    Prev
    Next
    INDEX
    Explanations

    references to sports programs and events

    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
    ü
    -0.06
    orsk
    -0.06
    azz
    -0.06
    IMIT
    -0.06
    KK
    -0.06
    alyzer
    -0.06
     football
    -0.06
    acÃŃ
    -0.06
    iera
    -0.06
     pret
    -0.06
    POSITIVE LOGITS
     USS
    0.08
     sanction
    0.08
     offic
    0.07
     federation
    0.07
     Amateur
    0.07
     member
    0.07
    _hooks
    0.07
    pickle
    0.07
    agues
    0.07
     youth
    0.07
    Activations Density 0.036%

    No Known Activations