© 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. 11-RESID-POST-AA
    11. 20765
    Prev
    Next
    INDEX
    Explanations

    finding settings/options

    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
    Bang
    -0.08
    mail
    -0.08
    apses
    -0.07
    lood
    -0.07
    lobal
    -0.07
    ematics
    -0.07
    _count
    -0.07
    weights
    -0.06
     lique
    -0.06
     '#'
    -0.06
    POSITIVE LOGITS
    ีร
    0.07
     withdraw
    0.06
     pakistan
    0.06
     피
    0.06
    แนะ
    0.06
    ANCEL
    0.06
    цион
    0.06
    _dest
    0.06
    nez
    0.05
    icho
    0.05
    Activations Density 0.068%

    No Known Activations