© 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. 23-RESID-POST-AA
    11. 66136
    Prev
    Next
    INDEX
    Explanations

    alcan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _prefs
    -0.07
    _epi
    -0.06
     kontakte
    -0.06
    -*
    -0.06
     Kami
    -0.06
     hepatitis
    -0.06
     primitive
    -0.06
     Negro
    -0.06
    atitis
    -0.06
    数据库
    -0.06
    POSITIVE LOGITS
     ความ
    0.07
    ulnerable
    0.06
    scient
    0.06
     alcan
    0.06
     مغ
    0.06
    โครงการ
    0.06
     타
    0.06
    caff
    0.06
    募
    0.06
     Achie
    0.06
    Activations Density 0.001%

    No Known Activations