© 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. 7-RESID-POST-AA
    11. 6168
    Prev
    Next
    INDEX
    Explanations

    suite

    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
    ナル
    -0.07
     Phon
    -0.07
     англ
    -0.06
    モン
    -0.06
    oldem
    -0.06
     imagin
    -0.06
    ).(
    -0.06
    lds
    -0.06
     kred
    -0.06
     HID
    -0.06
    POSITIVE LOGITS
     suite
    0.19
     Suite
    0.18
    Suite
    0.15
     suites
    0.14
    suite
    0.12
    _suite
    0.12
    uite
    0.11
     Suites
    0.11
     ensuite
    0.09
    -suite
    0.08
    Activations Density 0.003%

    No Known Activations