© 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. 118967
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     POT
    -0.07
     critique
    -0.06
    —is
    -0.06
    570
    -0.06
    다운
    -0.06
    896
    -0.06
    STAR
    -0.06
     Noah
    -0.06
     Owners
    -0.06
     Кол
    -0.06
    POSITIVE LOGITS
     deem
    0.07
    <|start_header_id|>
    0.07
     <=>
    0.06
    techn
    0.06
    :String
    0.06
    )")↵↵
    0.06
    děla
    0.06
     sleeping
    0.06
    četně
    0.06
     certif
    0.06
    Activations Density 0.027%

    No Known Activations