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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68919
    Prev
    Next
    INDEX
    Explanations

    bar

    np_max-act · gemini-2.0-flash

    This neuron detects HTML navigation‐bar markup, activating on occurrences of “bar” in class or id attributes related to nav bars.

    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
    ("../
    -0.07
     contato
    -0.06
    "How
    -0.06
     crop
    -0.06
    aud
    -0.06
    omatic
    -0.06
    ()(
    -0.06
    №№
    -0.06
    contrast
    -0.06
    适
    -0.06
    POSITIVE LOGITS
     bn
    0.06
     skyline
    0.06
    Guard
    0.06
     Gly
    0.06
    άν
    0.06
     dbus
    0.06
     비
    0.06
     decals
    0.06
     แพ
    0.06
    /meta
    0.06
    Activations Density 0.000%

    No Known Activations