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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 9879
    Prev
    Next
    INDEX
    Explanations

    Grenada/Grenfell

    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
    cj
    -0.06
    <s
    -0.06
    tat
    -0.06
    될
    -0.06
    间
    -0.06
    λογ
    -0.06
    <r
    -0.06
    _est
    -0.06
     ballot
    -0.05
    Initializer
    -0.05
    POSITIVE LOGITS
     progression
    0.07
    URNS
    0.07
     Planned
    0.07
     withdraw
    0.07
    acula
    0.06
     Enforcement
    0.06
     Cumhurbaşkanı
    0.06
     männ
    0.06
     linked
    0.06
    ZA
    0.06
    Activations Density 0.003%

    No Known Activations