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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57614
    Prev
    Next
    INDEX
    Explanations

    references to cultural celebrations or traditions

    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
    STA
    -0.08
    former
    -0.07
    eca
    -0.06
    åĨĴ
    -0.06
     çī
    -0.06
     nik
    -0.06
    çĻ¾
    -0.06
    izza
    -0.06
    iker
    -0.06
    iquer
    -0.06
    POSITIVE LOGITS
     Clan
    0.07
    pled
    0.07
     McLaren
    0.07
    istringstream
    0.07
     pled
    0.06
    tainment
    0.06
     Hearth
    0.06
    $MESS
    0.06
    ANDLE
    0.06
    :\/\/
    0.06
    Activations Density 0.001%

    No Known Activations