© 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. 6003
    Prev
    Next
    INDEX
    Explanations

    -west

    np_max-act · gemini-2.0-flash

    The neuron activates on compass direction terms, especially “west” and its compounds (e.g. “north-west,” “western,” “northwest”).

    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
    ait
    -0.07
     aider
    -0.07
    ful
    -0.07
    ieces
    -0.07
     NavParams
    -0.07
    に入
    -0.06
    .Mutable
    -0.06
     Mand
    -0.06
     Dynasty
    -0.06
    Hair
    -0.06
    POSITIVE LOGITS
     west
    0.08
     West
    0.07
     utiliz
    0.07
     ="
    0.06
    -х
    0.06
    -west
    0.06
     assignable
    0.06
    )(
    0.06
    ylan
    0.06
     Western
    0.06
    Activations Density 0.014%

    No Known Activations