© 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. 15-RESID-POST-AA
    11. 2339
    Prev
    Next
    INDEX
    Explanations

    partial words

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ON
    -0.07
    or
    -0.07
    ION
    -0.07
    ins
    -0.07
    obuf
    -0.07
    ior
    -0.07
    ion
    -0.07
    ons
    -0.07
    ン
    -0.07
     Harris
    -0.07
    POSITIVE LOGITS
    e
    0.13
    E
    0.12
    ge
    0.12
     e
    0.11
     E
    0.11
    (e
    0.11
    be
    0.11
    ве
    0.11
    .E
    0.11
    he
    0.11
    Activations Density 1.199%

    No Known Activations