© 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. 91337
    Prev
    Next
    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash

    This neuron detects the numeric accession‐type identifier that follows the “Access(ion) Number:” label.

    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
    porter
    -0.08
     мног
    -0.08
    UPLOAD
    -0.07
     referees
    -0.07
     CON
    -0.07
    holes
    -0.07
     Fair
    -0.07
    (language
    -0.07
     quote
    -0.07
     counting
    -0.07
    POSITIVE LOGITS
    یا
    0.06
    _MUL
    0.06
    underscore
    0.06
     THESE
    0.06
     provoz
    0.05
    щих
    0.05
     Gree
    0.05
     menggunakan
    0.05
     AVR
    0.05
    ivative
    0.05
    Activations Density 0.001%

    No Known Activations