© 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. 9-LLAMASCOPE-RES-131K
    11. 95642
    Prev
    Next
    INDEX
    Explanations

    references to contact lenses

    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
    /Library
    -0.08
     Slo
    -0.07
    OrNull
    -0.06
    ittest
    -0.06
     (?)
    -0.06
    angi
    -0.06
    ansi
    -0.06
    haust
    -0.06
    hill
    -0.06
    iesta
    -0.06
    POSITIVE LOGITS
     Joh
    0.06
    ief
    0.06
     favicon
    0.06
    SError
    0.06
    Äįi
    0.06
    efon
    0.06
    869
    0.06
    368
    0.06
    gend
    0.06
    -only
    0.05
    Activations Density 0.001%

    No Known Activations