© 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. 54137
    Prev
    Next
    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash

    The neuron activates on version identifiers and related keywords, especially semantic version strings (numerical sequences separated by dots) and “version” markers.

    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
    Ст
    -0.06
     Freeman
    -0.06
    tokenizer
    -0.06
     COMPUT
    -0.06
     دارای
    -0.06
     Netflix
    -0.06
     Shutterstock
    -0.06
    (isolate
    -0.06
    ertools
    -0.06
    Formatted
    -0.06
    POSITIVE LOGITS
    width
    0.08
    .ep
    0.07
    );
    ↵
    ↵
    0.07
    erior
    0.07
        ↵↵
    0.07
    ázky
    0.07
    곡
    0.07
    يلي
    0.07
    iyah
    0.07
    Handles
    0.06
    Activations Density 0.007%

    No Known Activations