© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 53382
    Prev
    Next
    INDEX
    Explanations

    brackets

    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
     Bakan
    -0.06
    765
    -0.06
    怖
    -0.06
    ้าหน
    -0.06
     molt
    -0.06
     CDN
    -0.06
    eel
    -0.06
     disastr
    -0.06
    nému
    -0.06
     fv
    -0.06
    POSITIVE LOGITS
    .Step
    0.07
    =============↵
    0.07
     yapmak
    0.07
    Tables
    0.07
     waterfall
    0.07
    reflection
    0.06
    بی
    0.06
    OLA
    0.06
     metaph
    0.06
     yaptık
    0.06
    Activations Density 0.039%

    No Known Activations