© 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. 11-RESID-POST-AA
    11. 52782
    Prev
    Next
    INDEX
    Explanations

    rac

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     сахар
    -0.07
    actical
    -0.07
    266
    -0.07
    OPT
    -0.07
     Athletic
    -0.07
    ystal
    -0.07
    izona
    -0.07
     &[
    -0.06
     Victim
    -0.06
     silicon
    -0.06
    POSITIVE LOGITS
     Brad
    0.10
    �
    0.09
     Brock
    0.09
    роб
    0.08
    r
    0.08
     Brent
    0.08
     RJ
    0.08
    ram
    0.08
    rin
    0.08
     Crawford
    0.08
    Activations Density 0.509%

    No Known Activations