© 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. 29667
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens—especially floating‐point or decimal numbers—wherever they appear.

    oai_token-act-pair · o4-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
     FOR
    -0.07
    ực
    -0.07
    (MSG
    -0.07
     Joel
    -0.06
    Rent
    -0.06
     Alien
    -0.06
    猛
    -0.06
     hotter
    -0.06
    roid
    -0.06
     horn
    -0.06
    POSITIVE LOGITS
     Lap
    0.07
    ooo
    0.07
     trainer
    0.06
     πα
    0.06
     değişiklik
    0.06
     tweets
    0.06
     ак
    0.06
     Ek
    0.06
    _flight
    0.06
    래스
    0.06
    Activations Density 0.035%

    No Known Activations