© 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. 53109
    Prev
    Next
    INDEX
    Explanations

    -ing

    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
     bored
    -0.06
     Photon
    -0.06
     stringByAppendingString
    -0.06
     hustle
    -0.06
     Former
    -0.06
     trivial
    -0.06
    ERO
    -0.06
     Find
    -0.06
    \Desktop
    -0.06
    (latitude
    -0.06
    POSITIVE LOGITS
     mücadele
    0.07
    enko
    0.07
     plaint
    0.06
    prices
    0.06
     thép
    0.06
     BITS
    0.06
     statuses
    0.06
     blok
    0.06
    soc
    0.06
    kám
    0.06
    Activations Density 0.116%

    No Known Activations