© 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. 19-RESID-POST-AA
    11. 71084
    Prev
    Next
    INDEX
    Explanations

    At

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     데이터
    -0.07
    _de
    -0.07
    ots
    -0.06
    ILE
    -0.06
    	ctrl
    -0.06
     bardzo
    -0.06
     ion
    -0.06
     child
    -0.06
    masters
    -0.06
    cot
    -0.06
    POSITIVE LOGITS
    -create
    0.07
    .getSystemService
    0.07
    џџџџџџџџ
    0.06
     rowIndex
    0.06
     Plugin
    0.06
     imprison
    0.06
    ､_
    0.06
    .omg
    0.06
    -Mail
    0.06
     واقع
    0.06
    Activations Density 0.068%

    No Known Activations