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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 25332
    Prev
    Next
    INDEX
    Explanations

    airplanes and transportation

    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
     enumerator
    -0.06
     tud
    -0.06
    .fx
    -0.06
     Democr
    -0.06
    urrency
    -0.06
     Britann
    -0.06
     setUser
    -0.06
    chapter
    -0.06
    weapons
    -0.06
    ク
    -0.06
    POSITIVE LOGITS
     SJ
    0.07
     afflict
    0.07
     coi
    0.07
    _DO
    0.06
     administered
    0.06
    ți
    0.06
    оки
    0.06
     affiliated
    0.06
    CONT
    0.06
     chilly
    0.06
    Activations Density 2.014%

    No Known Activations