© 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. 126985
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron responds to standalone numeric literals (tokens composed of digits or simple numbers).

    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
    ूह
    -0.07
    daughter
    -0.07
    _State
    -0.07
     sermon
    -0.07
    																			
    -0.06
     characters
    -0.06
    (ht
    -0.06
    ứt
    -0.06
    														
    -0.06
    다면
    -0.06
    POSITIVE LOGITS
    [start
    0.06
    locate
    0.06
     роботи
    0.06
    .work
    0.06
     раза
    0.06
     interiors
    0.06
     onstage
    0.06
     fisse
    0.06
    .sum
    0.06
     atte
    0.06
    Activations Density 0.007%

    No Known Activations