© 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. 7-RESID-POST-AA
    11. 25076
    Prev
    Next
    INDEX
    Explanations

    Legal jurisdiction/registration

    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
     collusion
    -0.06
    σή
    -0.06
    uja
    -0.06
    稱
    -0.06
     reinterpret
    -0.06
    (search
    -0.06
    73
    -0.06
    yen
    -0.06
    -secondary
    -0.06
    阅
    -0.06
    POSITIVE LOGITS
    webElement
    0.07
    ро
    0.07
     cosmic
    0.07
    (({
    0.06
    pushViewController
    0.06
     insecurity
    0.06
    hledem
    0.06
     Dish
    0.06
    .city
    0.06
     Problems
    0.06
    Activations Density 0.076%

    No Known Activations