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. 28630
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Differences
    -0.07
    iếu
    -0.06
     compartments
    -0.06
     suits
    -0.06
    建設
    -0.06
     detective
    -0.06
     franchises
    -0.06
    Il
    -0.06
     getParent
    -0.06
     suit
    -0.06
    POSITIVE LOGITS
     Powered
    0.07
     Olive
    0.07
    (Self
    0.07
     dessa
    0.07
    GestureRecognizer
    0.07
     CGRectMake
    0.06
    اشة
    0.06
    &o
    0.06
     první
    0.06
    ("\(
    0.06
    Activations Density 0.068%

    No Known Activations