© 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. 110382
    Prev
    Next
    INDEX
    Explanations

    sensitive skin

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “dry” conditions (e.g. dry hair or dry skin).

    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
    Jay
    -0.08
     Nora
    -0.06
     prostitutas
    -0.06
     chiar
    -0.06
    .entry
    -0.06
     Converter
    -0.06
     nationally
    -0.06
    stances
    -0.06
    ゞ
    -0.06
    imator
    -0.06
    POSITIVE LOGITS
     LARGE
    0.08
     Bên
    0.07
     Jahren
    0.07
     HISTORY
    0.06
    %,
    0.06
     sensation
    0.06
     Identify
    0.06
    asString
    0.06
     Mine
    0.06
    Und
    0.06
    Activations Density 0.020%

    No Known Activations