© 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. 23-RESID-POST-AA
    11. 105534
    Prev
    Next
    INDEX
    Explanations

    desired

    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
    most
    -0.07
    form
    -0.07
    kom
    -0.07
    EL
    -0.07
    arsi
    -0.07
    lid
    -0.06
    1
    -0.06
     ngờ
    -0.06
    substring
    -0.06
    لى
    -0.06
    POSITIVE LOGITS
    warnings
    0.06
     autism
    0.06
     walked
    0.06
     CSP
    0.06
    (sp
    0.06
    .getColumnModel
    0.06
     Late
    0.06
     coursework
    0.06
    .Assertions
    0.05
    Late
    0.05
    Activations Density 0.202%

    No Known Activations