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. 30912
    Prev
    Next
    INDEX
    Explanations

    .href

    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
    <label
    -0.07
    ۱۰
    -0.07
     controller
    -0.06
    bie
    -0.06
    -buffer
    -0.06
    ick
    -0.06
    icks
    -0.06
    _Rect
    -0.06
     клуб
    -0.06
     Act
    -0.06
    POSITIVE LOGITS
     {@
    0.07
     subsid
    0.07
     prive
    0.06
    слід
    0.06
     وإ
    0.06
    dfunding
    0.06
     Cumhur
    0.06
     возду
    0.06
    .offsetTop
    0.06
    _ATTR
    0.06
    Activations Density 0.001%

    No Known Activations