© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 97178
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    user-style instructional prompts with first- and second-person pronouns indicating requests or roles in a conversational setup.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    msgid
    -0.07
     Cub
    -0.06
    instances
    -0.06
    BUTTON
    -0.06
    ?',↵
    -0.06
     compat
    -0.06
    em
    -0.06
    śmy
    -0.06
    isors
    -0.06
    %%
    -0.06
    POSITIVE LOGITS
    ælland
    0.07
     withdraw
    0.06
     Coleman
    0.06
     Jenn
    0.06
    /oct
    0.06
     Mustafa
    0.06
    (employee
    0.06
    .click
    0.06
    警察
    0.06
     ))↵
    0.06
    Activations Density 0.702%

    No Known Activations