© 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. 19-RESID-POST-AA
    6. 84932
    Prev
    Next
    INDEX
    Explanations

    pen

    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
    _routing
    -0.06
     fait
    -0.06
     faction
    -0.06
    oralType
    -0.06
     Bast
    -0.06
    "T
    -0.06
     Charlotte
    -0.06
     nová
    -0.06
    .gameObject
    -0.05
     Τ
    -0.05
    POSITIVE LOGITS
     Pen
    0.09
    Pen
    0.09
     pen
    0.09
     penis
    0.08
     pencil
    0.08
     penn
    0.08
    ে
    0.07
    enn
    0.07
    بر
    0.07
     Penalty
    0.07
    Activations Density 0.025%

    No Known Activations