© 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. 15-LLAMASCOPE-RES-131K
    11. 103831
    Prev
    Next
    INDEX
    Explanations

    terms related to cultural identity and expressions in Caribbean literature

    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
    ilter
    -0.06
     procedure
    -0.06
    unte
    -0.06
     Pis
    -0.06
    ipar
    -0.06
     grate
    -0.06
    Tower
    -0.05
    ypo
    -0.05
    ÏĢιÏĥ
    -0.05
    tero
    -0.05
    POSITIVE LOGITS
    odash
    0.07
    ÑĪÑĤ
    0.06
    ÑĪин
    0.06
    oup
    0.06
     +#
    0.06
     Pols
    0.06
    eum
    0.06
    lew
    0.06
    clin
    0.06
    ocator
    0.06
    Activations Density 0.001%

    No Known Activations