© 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
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 35113
    Prev
    Next
    INDEX
    Explanations

    fantasy stories

    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
    viders
    -0.07
    >R
    -0.07
    /kg
    -0.06
    _CD
    -0.06
     Sexual
    -0.06
     Chevy
    -0.06
    estr
    -0.06
    /password
    -0.06
    uppies
    -0.06
    >List
    -0.06
    POSITIVE LOGITS
    	logging
    0.06
     parms
    0.06
     priceless
    0.06
    fixed
    0.06
    _OFF
    0.06
    (import
    0.06
    (base
    0.06
    utable
    0.06
    offs
    0.06
    ||↵
    0.05
    Activations Density 0.013%

    No Known Activations