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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 10087
    Prev
    Next
    INDEX
    Explanations

    leg

    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
    avery
    -0.07
     agli
    -0.07
    	mod
    -0.06
     headed
    -0.06
     uma
    -0.06
     ima
    -0.06
     dopo
    -0.06
     мод
    -0.06
    chantment
    -0.06
    toolStrip
    -0.06
    POSITIVE LOGITS
    	LEFT
    0.06
    aret
    0.06
     paperwork
    0.06
     Delicious
    0.06
    拍
    0.06
    inne
    0.06
     SET
    0.06
    驚
    0.06
    ypse
    0.06
     electronics
    0.06
    Activations Density 0.000%

    No Known Activations