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. 9511
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    ustain
    -0.07
    .Elements
    -0.06
    ?",
    -0.06
     khách
    -0.06
     passer
    -0.06
     Nun
    -0.06
     невозможно
    -0.06
    特殊
    -0.06
     (@
    -0.06
     برنامه
    -0.06
    POSITIVE LOGITS
    вищ
    0.07
     tint
    0.07
    _BITMAP
    0.07
    Third
    0.07
    labs
    0.06
    歳
    0.06
    087
    0.06
    ative
    0.06
    textAlign
    0.06
     suppress
    0.06
    Activations Density 0.012%

    No Known Activations