© 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. 7-RESID-POST-AA
    11. 46510
    Prev
    Next
    INDEX
    Explanations

    util

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    662
    -0.07
    Aspect
    -0.07
    persons
    -0.07
    しゃ
    -0.06
     dungeon
    -0.06
     asses
    -0.06
     Roma
    -0.06
    SEND
    -0.06
    abcdefghijklmnopqrstuvwxyz
    -0.06
    uggested
    -0.06
    POSITIVE LOGITS
     clutter
    0.07
     mus
    0.06
     TAS
    0.06
     당
    0.06
     optim
    0.06
    ocusing
    0.06
    Mus
    0.06
     Beckham
    0.06
     Han
    0.06
     Gecko
    0.06
    Activations Density 0.061%

    No Known Activations