© 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. 19-RESID-POST-AA
    11. 87711
    Prev
    Next
    INDEX
    Explanations

    the

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]))
    -0.07
    異
    -0.07
     conspic
    -0.07
     dvd
    -0.06
     Созд
    -0.06
    ський
    -0.06
    mult
    -0.06
     上海
    -0.06
    hev
    -0.06
    ，又
    -0.05
    POSITIVE LOGITS
    (epoch
    0.07
    .Min
    0.07
    acement
    0.07
    "context
    0.06
     famille
    0.06
     noh
    0.06
     UserController
    0.06
    cession
    0.06
    (balance
    0.06
    ?[
    0.06
    Activations Density 0.029%

    No Known Activations