© 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. 10865
    Prev
    Next
    INDEX
    Explanations

    an

    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
     transformed
    -0.07
     Must
    -0.06
     advertisements
    -0.06
     pump
    -0.06
    plement
    -0.06
    kům
    -0.06
     Application
    -0.06
    	E
    -0.06
     Marijuana
    -0.06
     formulations
    -0.06
    POSITIVE LOGITS
     Báo
    0.06
    (completion
    0.06
     HEL
    0.06
    bour
    0.06
    _refs
    0.06
     홍
    0.06
    (rename
    0.06
    .REACT
    0.06
     createdAt
    0.06
     tecr
    0.06
    Activations Density 0.012%

    No Known Activations