Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 112039
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     область
    -0.07
    ContentType
    -0.07
     always
    -0.06
     dancer
    -0.06
     Shots
    -0.06
    代表
    -0.06
    途
    -0.06
    廣
    -0.06
     dio
    -0.06
    	panic
    -0.06
    POSITIVE LOGITS
     ід
    0.07
    (cluster
    0.07
    tele
    0.07
    ožná
    0.06
    Bindings
    0.06
    /",
    0.06
     peculiar
    0.06
    .getColor
    0.06
    ias
    0.06
    Eu
    0.06
    Activations Density 0.214%

    No Known Activations