© 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. 19-RESID-POST-AA
    6. 57741
    Prev
    Next
    INDEX
    Explanations

    ich

    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
     البحر
    -0.07
    _unique
    -0.07
     blue
    -0.06
     nhanh
    -0.06
    we
    -0.06
    bull
    -0.06
     dumb
    -0.06
     hundred
    -0.06
    icing
    -0.06
     Hipp
    -0.06
    POSITIVE LOGITS
     beled
    0.06
    :return
    0.06
    ImageContext
    0.06
    ΙΤ
    0.06
     gag
    0.06
     //////////////////////////////////
    0.06
     titleLabel
    0.06
    _RS
    0.06
     Variation
    0.06
     excav
    0.06
    Activations Density 0.005%

    No Known Activations