© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 29966
    Prev
    Next
    INDEX
    Explanations

    Systems, threats

    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
    nosis
    -0.07
     courts
    -0.06
    znik
    -0.06
     �
    -0.06
    /J
    -0.06
     admitting
    -0.06
    Params
    -0.06
     Ün
    -0.06
     tránh
    -0.06
    =forms
    -0.05
    POSITIVE LOGITS
     consideration
    0.07
    .placeholder
    0.07
    дав
    0.07
    electron
    0.07
    	ft
    0.06
     gatherings
    0.06
     modest
    0.06
     dietary
    0.06
     rebuild
    0.06
    ава
    0.06
    Activations Density 0.003%

    No Known Activations