© 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. 29932
    Prev
    Next
    INDEX
    Explanations

    code updates

    np_max-act · gemini-2.0-flash

    This neuron detects the common imperative action verbs (e.g. “Fixed,” “Added,” “Remove,” “Backport,” “Update,” “Changed,” “Use,” etc.) that introduce entries in a software changelog.

    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
    .conn
    -0.07
    getChild
    -0.07
    ]])
    -0.06
    .callbacks
    -0.06
    .sav
    -0.06
     année
    -0.06
     Там
    -0.06
    _CUSTOMER
    -0.06
    .Att
    -0.06
    utow
    -0.06
    POSITIVE LOGITS
    (--
    0.07
    ATIO
    0.06
    isable
    0.06
    lıklı
    0.06
    -y
    0.06
     realidad
    0.06
     læ
    0.06
     输入
    0.06
    icked
    0.06
    atively
    0.06
    Activations Density 0.011%

    No Known Activations