© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 103723
    Prev
    Next
    INDEX
    Explanations

    violation

    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
     imagination
    -0.07
     adjective
    -0.06
    .MAX
    -0.06
    ZZ
    -0.06
    external
    -0.06
    medicine
    -0.06
    ・マ
    -0.06
    tml
    -0.06
    PM
    -0.06
     Accessories
    -0.06
    POSITIVE LOGITS
     violations
    0.09
     violation
    0.08
    ident
    0.08
     viol
    0.08
     Viol
    0.08
    违
    0.08
    -viol
    0.08
     tieten
    0.08
     će
    0.07
     violate
    0.07
    Activations Density 0.010%

    No Known Activations