© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56605
    Prev
    Next
    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting decimal‐point number tokens (e.g., “.03”, “.14”, “.369”).

    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
    保护
    -0.06
    endcode
    -0.06
    誉
    -0.06
    otechn
    -0.06
    xbb
    -0.06
    립니다
    -0.06
    ICON
    -0.06
    ravel
    -0.06
    wit
    -0.06
    >t
    -0.06
    POSITIVE LOGITS
     cái
    0.08
    (graph
    0.07
    照片
    0.07
    abilecek
    0.06
     e
    0.06
     '-
    0.06
     copies
    0.06
     schema
    0.06
    載
    0.06
    	direction
    0.06
    Activations Density 0.000%

    No Known Activations