© 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. 16505
    Prev
    Next
    INDEX
    Explanations

    mentions of events and festivals

    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
    449
    -0.07
    rvine
    -0.07
    inox
    -0.07
    Enlarge
    -0.07
    839
    -0.06
    kop
    -0.06
     trÃł
    -0.06
    ÑĬ
    -0.06
    eÄį
    -0.06
    ahun
    -0.06
    POSITIVE LOGITS
     Whites
    0.06
    èĽ
    0.06
     cul
    0.06
    acts
    0.06
     activation
    0.06
    activation
    0.06
    credential
    0.06
     acts
    0.06
     Activation
    0.06
     Peoples
    0.06
    Activations Density 0.014%

    No Known Activations