Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 112333
    Prev
    Next
    INDEX
    Explanations

    scientific/experimental procedures

    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
     stitched
    -0.07
     software
    -0.07
     followers
    -0.06
    mad
    -0.06
     cab
    -0.06
     sent
    -0.06
     hurried
    -0.06
    飞
    -0.06
     Gund
    -0.06
    amped
    -0.06
    POSITIVE LOGITS
     Rehabilitation
    0.07
    NavBar
    0.07
    >{{$
    0.06
    >{↵
    0.06
     eksik
    0.06
     مسئله
    0.06
    NewItem
    0.06
     Econ
    0.06
     můž
    0.06
    centage
    0.06
    Activations Density 0.127%

    No Known Activations