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. 7-RESID-POST-AA
    6. 112623
    Prev
    Next
    INDEX
    Explanations

    in

    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
     McCorm
    -0.06
     intercepted
    -0.06
    represented
    -0.06
    GetSize
    -0.06
    ########################################################
    -0.06
     spice
    -0.06
     receptor
    -0.06
     receptors
    -0.06
    /perl
    -0.06
     향
    -0.06
    POSITIVE LOGITS
     BO
    0.07
    ικοί
    0.07
    。(
    0.06
     मन
    0.06
    LayoutInflater
    0.06
     arson
    0.06
    [H
    0.06
     Guar
    0.06
     Faker
    0.06
     ко
    0.06
    Activations Density 0.058%

    No Known Activations