© 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. 9289
    Prev
    Next
    INDEX
    Explanations

    Code symbols

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers) in code.

    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
    .imwrite
    -0.07
    .story
    -0.07
    observable
    -0.07
     intestine
    -0.07
     Sanctuary
    -0.06
     {},
    -0.06
    -info
    -0.06
    ke
    -0.06
     manifest
    -0.06
     errores
    -0.06
    POSITIVE LOGITS
    ように
    0.06
    営
    0.06
    upply
    0.06
    接着
    0.06
     =$
    0.06
     exhausted
    0.06
    esign
    0.06
    -written
    0.06
     eigentlich
    0.06
    などの
    0.06
    Activations Density 0.014%

    No Known Activations