© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123477
    Prev
    Next
    INDEX
    Explanations

    hn

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agnet
    -0.08
     Ja
    -0.07
    333
    -0.07
     حی
    -0.07
     Kürt
    -0.06
     £
    -0.06
    _km
    -0.06
     leur
    -0.06
     має
    -0.06
     reput
    -0.06
    POSITIVE LOGITS
     probation
    0.14
     sectional
    0.12
     ITV
    0.11
    .this
    0.08
    )sender
    0.07
    的地方
    0.07
     compelling
    0.06
     cách
    0.06
    除了
    0.06
    /disable
    0.06
    Activations Density 0.003%

    No Known Activations