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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31081
    Prev
    Next
    INDEX
    Explanations

    Household items and food

    np_max-act · gemini-2.0-flash

    methods for removing adhesive residues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on names of specific substances or ingredients (e.g. soaps, oils, vinegars, salts, etc.) used in home‐remedy, cleaning, or pest‐control recipes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crc
    -0.07
    ATIONS
    -0.07
    AffineTransform
    -0.06
    .GeneratedValue
    -0.06
     condemning
    -0.06
    -generated
    -0.06
     theft
    -0.06
     Serializable
    -0.06
    OCKET
    -0.06
     эффек
    -0.06
    POSITIVE LOGITS
    >↵↵
    0.07
    /*/
    0.07
     代
    0.06
    >↵
    0.06
    }↵↵
    0.06
     Ekim
    0.06
    下去
    0.06
    italic
    0.06
    itte
    0.06
    {},
    0.06
    Activations Density 0.022%

    No Known Activations