© 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. 30018
    Prev
    Next
    INDEX
    Explanations

    adverbs of certainty/probability

    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
     is
    -0.08
     would
    -0.07
     can
    -0.06
     feels
    -0.06
    (Create
    -0.06
    ίναι
    -0.06
     residues
    -0.06
     hears
    -0.06
     філь
    -0.06
    OTP
    -0.06
    POSITIVE LOGITS
    _actual
    0.07
    .JpaRepository
    0.06
    ิทยาศาสตร
    0.06
     Tac
    0.06
     Waterloo
    0.06
     después
    0.06
    ************************
    0.06
     removeAll
    0.06
    至少
    0.06
     posledních
    0.06
    Activations Density 0.086%

    No Known Activations