© 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. 129934
    Prev
    Next
    INDEX
    Explanations

    a, the

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on simple past‐tense verbs (e.g. “lived,” “worked,” “continued”).

    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
    -for
    -0.07
    .Fl
    -0.07
     On
    -0.07
    šla
    -0.07
     apex
    -0.07
     certified
    -0.06
     House
    -0.06
     каж
    -0.06
     Off
    -0.06
     sắp
    -0.06
    POSITIVE LOGITS
     a
    0.08
    stored
    0.07
    whole
    0.07
    variable
    0.07
    Static
    0.07
    cash
    0.06
     lining
    0.06
    لمه
    0.06
     huh
    0.06
    READY
    0.06
    Activations Density 0.087%

    No Known Activations