© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 52183
    Prev
    Next
    INDEX
    Explanations

    is

    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
     сил
    -0.07
     accuse
    -0.07
     результат
    -0.07
     dire
    -0.07
     subdued
    -0.07
    еної
    -0.07
    θη
    -0.07
    そう
    -0.06
     Orient
    -0.06
     Buccane
    -0.06
    POSITIVE LOGITS
    .required
    0.06
    Dealer
    0.06
     trilogy
    0.06
    :disable
    0.06
    fon
    0.06
     Dealer
    0.06
    醫
    0.06
    絶
    0.06
    POSITE
    0.06
    recommended
    0.06
    Activations Density 0.046%

    No Known Activations