© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 62740
    Prev
    Next
    INDEX
    Explanations

    how about

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
           
    -0.07
     praž
    -0.06
    NSAttributedString
    -0.06
     stupidity
    -0.06
     Compound
    -0.06
    _Print
    -0.06
     привести
    -0.06
    _UNIX
    -0.06
    	sw
    -0.06
    hunt
    -0.06
    POSITIVE LOGITS
     желез
    0.06
     травня
    0.06
    roducing
    0.06
    -using
    0.06
    为了
    0.06
     Calc
    0.06
    ENS
    0.06
    ver
    0.06
    VER
    0.06
    Qu
    0.06
    Activations Density 0.005%

    No Known Activations