© 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. 126755
    Prev
    Next
    INDEX
    Explanations

    the name "Stan," indicating a focus on references to individuals named Stan

    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
    yat
    -0.07
    imin
    -0.07
    yi
    -0.07
    andering
    -0.07
    isten
    -0.06
    tin
    -0.06
    icont
    -0.06
    periment
    -0.06
    éĥİ
    -0.06
    space
    -0.06
    POSITIVE LOGITS
    islav
    0.09
    vation
    0.07
    phyl
    0.07
    ells
    0.07
    наÑĢ
    0.07
    θεÏģ
    0.06
    chez
    0.06
    bury
    0.06
    ards
    0.06
    SETTINGS
    0.06
    Activations Density 0.010%

    No Known Activations