© 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. 11-RESID-POST-AA
    6. 77047
    Prev
    Next
    INDEX
    Explanations

    ior

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Panda
    -0.07
    _TRANSACTION
    -0.07
     Oaks
    -0.07
    (status
    -0.07
    .Errorf
    -0.07
    ニニ
    -0.06
     тепло
    -0.06
    (ca
    -0.06
    .inline
    -0.06
     paddingTop
    -0.06
    POSITIVE LOGITS
    .Players
    0.07
    orry
    0.06
     fotoğraf
    0.06
    Instrument
    0.06
     Daughter
    0.06
     entries
    0.06
     ingl
    0.06
     Detail
    0.06
     služ
    0.06
     Hungary
    0.06
    Activations Density 0.000%

    No Known Activations