© 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. 11-RESID-POST-AA
    6. 24946
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    sentences that express uncomfortable or patronizing reactions to people with disabilities in social contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unnecessary
    -0.07
    taboola
    -0.06
    236
    -0.06
    _NEW
    -0.06
    员
    -0.06
     مور
    -0.06
    _annotation
    -0.06
    /values
    -0.06
    clamation
    -0.06
     Snapshot
    -0.06
    POSITIVE LOGITS
     Inch
    0.07
     succes
    0.06
     Arrays
    0.06
     congregation
    0.06
    ,ID
    0.06
    Ub
    0.06
     گاه
    0.06
    errors
    0.06
    _pas
    0.06
    (lon
    0.06
    Activations Density 0.000%

    No Known Activations