© 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. 25133
    Prev
    Next
    INDEX
    Explanations

    strict

    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
    显示
    -0.07
    -gnu
    -0.07
    —but
    -0.06
    xaf
    -0.06
     Twe
    -0.06
    植
    -0.06
    'aut
    -0.06
     поход
    -0.06
    —and
    -0.06
    不同
    -0.06
    POSITIVE LOGITS
    Toy
    0.07
     FIX
    0.07
    ioned
    0.07
     сайте
    0.06
     Erotic
    0.06
     IsActive
    0.06
     Env
    0.06
    asury
    0.06
     Pt
    0.06
    stellung
    0.06
    Activations Density 0.002%

    No Known Activations