© 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. 3-RESID-POST-AA
    11. 95278
    Prev
    Next
    INDEX
    Explanations

    warnings

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oured
    -0.07
    pressions
    -0.06
    ,’
    -0.06
    ровод
    -0.06
     Neil
    -0.06
    tokenizer
    -0.06
    ologna
    -0.06
    .Sdk
    -0.06
    andoned
    -0.06
     proposed
    -0.06
    POSITIVE LOGITS
     beware
    0.18
     Hera
    0.12
     PUBLIC
    0.12
    eware
    0.11
     Bew
    0.08
     sessionStorage
    0.07
    .PRO
    0.07
     marché
    0.07
    려고
    0.07
    _CREATE
    0.07
    Activations Density 0.002%

    No Known Activations