© 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. 15-RESID-POST-AA
    6. 91772
    Prev
    Next
    INDEX
    Explanations

    :

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     synt
    -0.07
     true
    -0.07
     Costco
    -0.06
     relativ
    -0.06
     moz
    -0.06
     Exchange
    -0.06
    DataProvider
    -0.06
     FactoryBot
    -0.06
    Activities
    -0.06
     Hwy
    -0.06
    POSITIVE LOGITS
    oley
    0.07
    pline
    0.06
    >Please
    0.06
    aac
    0.06
     bisa
    0.06
    _fds
    0.06
    .getUserId
    0.06
     大阪
    0.06
    .dump
    0.06
    BTTag
    0.06
    Activations Density 0.048%

    No Known Activations