© 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. 124920
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron mostly lights up on numeric tokens containing decimal points—that is, floating‐point 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
     SUPPORT
    -0.07
     �
    -0.07
     Support
    -0.07
    EMPLATE
    -0.06
     lure
    -0.06
     comprise
    -0.06
    税
    -0.06
     Lola
    -0.06
     Legal
    -0.06
     Stage
    -0.06
    POSITIVE LOGITS
    .Cart
    0.07
    .ogg
    0.06
    *ft
    0.06
     -*-↵↵
    0.06
     baud
    0.06
    -col
    0.06
     decency
    0.06
    ."</
    0.06
    Fantastic
    0.05
    kills
    0.05
    Activations Density 0.045%

    No Known Activations