© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 75597
    Prev
    Next
    INDEX
    Explanations

    uncertainty and questioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     humour
    -0.07
    γρά
    -0.07
     humor
    -0.07
    ्ड
    -0.07
    ün
    -0.06
     Việc
    -0.06
    urrency
    -0.06
    дя
    -0.06
    ats
    -0.06
    urg
    -0.06
    POSITIVE LOGITS
    fsp
    0.07
     pem
    0.07
     reperc
    0.06
    :H
    0.06
    "])
    0.06
    _equiv
    0.06
    Apollo
    0.06
     **)
    0.06
     reiterated
    0.06
    卷
    0.06
    Activations Density 0.310%

    No Known Activations