© 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. 16325
    Prev
    Next
    INDEX
    Explanations

    references to dishwashing and related kitchen appliances

    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
    zion
    -0.08
    otive
    -0.07
    gers
    -0.07
    ees
    -0.07
    ivec
    -0.07
    sert
    -0.06
    ulet
    -0.06
    QRS
    -0.06
    olini
    -0.06
     ninh
    -0.06
    POSITIVE LOGITS
    washer
    0.09
    ware
    0.08
    rait
    0.07
    y
    0.07
    argin
    0.07
    elle
    0.07
    onor
    0.07
    erman
    0.07
    wash
    0.07
    washing
    0.06
    Activations Density 0.002%

    No Known Activations