© 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
    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. 92390
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash

    The neuron detects modal constructions expressing how someone “would be” feeling or responding—especially phrases like “would be proud” or “would be humbled.”

    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
     emacs
    -0.07
    Medium
    -0.07
    757
    -0.07
    $LANG
    -0.07
    ToMany
    -0.07
     Emacs
    -0.06
     Schema
    -0.06
     getItem
    -0.06
     Lawrence
    -0.06
     lineWidth
    -0.06
    POSITIVE LOGITS
     можлив
    0.06
    matplotlib
    0.06
    ropping
    0.06
    303
    0.06
    Hang
    0.06
    _stats
    0.06
    اگ
    0.06
     hang
    0.06
     Finish
    0.06
     έχουν
    0.06
    Activations Density 0.033%

    No Known Activations