© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 11155
    Prev
    Next
    INDEX
    Explanations

    origins

    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
    INE
    -0.06
    assword
    -0.06
    aa
    -0.06
    Wind
    -0.06
    ampo
    -0.06
    -0.06
    '.
    -0.05
     Něm
    -0.05
    instructions
    -0.05
    zzle
    -0.05
    POSITIVE LOGITS
    _);↵↵
    0.07
    prung
    0.07
    	EIF
    0.07
     phil
    0.07
    (accounts
    0.07
    찬
    0.07
    俺は
    0.06
    itch
    0.06
    üncü
    0.06
     staggering
    0.06
    Activations Density 0.013%

    No Known Activations