© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123217
    Prev
    Next
    INDEX
    Explanations

    domain names

    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
    484
    -0.06
     parentheses
    -0.06
    warts
    -0.06
    ователь
    -0.06
     potion
    -0.06
     knocked
    -0.06
     Brew
    -0.06
    UTIL
    -0.06
    Ÿ
    -0.06
    punkt
    -0.06
    POSITIVE LOGITS
    .ca
    0.16
    .ie
    0.11
    .it
    0.11
    .no
    0.10
    .es
    0.10
    .dk
    0.10
    .nl
    0.09
    .fr
    0.09
    .ng
    0.09
    .cl
    0.09
    Activations Density 0.016%

    No Known Activations