© 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. 23-RESID-POST-AA
    11. 105002
    Prev
    Next
    INDEX
    Explanations

    imperfections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     título
    -0.07
     сьогодні
    -0.07
     ';
    -0.07
     cosine
    -0.07
     Solid
    -0.07
     sociedad
    -0.07
    пеки
    -0.06
    words
    -0.06
     意
    -0.06
    cd
    -0.06
    POSITIVE LOGITS
     Flam
    0.07
    PTION
    0.07
     �
    0.07
    ,var
    0.07
     flavored
    0.07
    др
    0.07
     flap
    0.07
     valign
    0.07
    ноч
    0.07
    .A
    0.07
    Activations Density 0.057%

    No Known Activations