© 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. 40513
    Prev
    Next
    INDEX
    Explanations

    tech versions/models

    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
    _Pin
    -0.08
    .St
    -0.07
     кл
    -0.07
    });↵
    -0.06
     Amir
    -0.06
     comprehend
    -0.06
     Pen
    -0.06
     Worm
    -0.06
    일
    -0.06
     Lans
    -0.06
    POSITIVE LOGITS
    「
    0.06
    ledo
    0.06
     Magazine
    0.06
    coal
    0.06
     beaucoup
    0.06
    bw
    0.06
    、二
    0.06
    _alarm
    0.06
     ตำ
    0.06
    $return
    0.06
    Activations Density 0.004%

    No Known Activations