© 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. 7-RESID-POST-AA
    6. 120042
    Prev
    Next
    INDEX
    Explanations

    contractions ending in n't

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    -0.07
     Maple
    -0.07
     carte
    -0.07
     ly
    -0.07
     analytic
    -0.06
    ly
    -0.06
    otropic
    -0.06
    *pi
    -0.06
    ,Object
    -0.06
     Tele
    -0.06
    POSITIVE LOGITS
     don
    0.18
     doesn
    0.18
     didn
    0.17
     isn
    0.16
     aren
    0.15
     couldn
    0.15
     wouldn
    0.15
     wasn
    0.14
     hasn
    0.14
     hadn
    0.14
    Activations Density 0.095%

    No Known Activations