© 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. 11-RESID-POST-AA
    6. 36836
    Prev
    Next
    INDEX
    Explanations

    ological

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Numer
    -0.08
    :-------------</
    -0.08
    (render
    -0.07
    <Text
    -0.07
    Text
    -0.07
    32
    -0.07
     Tester
    -0.07
     mænd
    -0.07
    Blank
    -0.07
     Bind
    -0.07
    POSITIVE LOGITS
     ecological
    0.13
     Ec
    0.11
     Eco
    0.10
     ecology
    0.09
    .ec
    0.08
    Ec
    0.08
    ког
    0.08
    EC
    0.08
     eco
    0.08
    /ec
    0.07
    Activations Density 0.010%

    No Known Activations