© 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. 56642
    Prev
    Next
    INDEX
    Explanations

    algorithm

    np_max-act · gemini-2.0-flash

    This neuron activates on technical programming or algorithm vocabulary—words like “factory,” “method,” and “algorithm” in code or software‐design contexts.

    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
     correlations
    -0.08
    íg
    -0.06
     commencement
    -0.06
     náp
    -0.06
    ergency
    -0.06
    یت
    -0.06
     підприємства
    -0.06
    youtube
    -0.05
     nhiệt
    -0.05
    شناسی
    -0.05
    POSITIVE LOGITS
    <!--
    0.07
    .proxy
    0.07
     PF
    0.07
    gb
    0.06
    cdn
    0.06
     CONF
    0.06
     ghost
    0.06
     Inspir
    0.06
    ?><
    0.06
    `()
    0.06
    Activations Density 0.267%

    No Known Activations