© 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. 40207
    Prev
    Next
    INDEX
    Explanations

    definitions

    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
    imler
    -0.07
    _alloc
    -0.07
    GPL
    -0.07
     عشق
    -0.07
     wrath
    -0.07
    RowAtIndexPath
    -0.07
     recur
    -0.07
    typeName
    -0.06
    items
    -0.06
    (BigInteger
    -0.06
    POSITIVE LOGITS
     generar
    0.06
    couldn
    0.06
    abel
    0.06
    setLabel
    0.06
    _TEST
    0.06
     ------------
    0.06
     '',
↵
    0.06
    indre
    0.06
    peek
    0.06
    facebook
    0.06
    Activations Density 0.156%

    No Known Activations