Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 1012
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash

    This neuron detects passive‐voice legal statements, especially instances of “is” or “are” followed by a past‐participle verb.

    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
     περί
    -0.07
    .JpaRepository
    -0.07
    神
    -0.06
    |M
    -0.06
    ColumnsMode
    -0.06
    phans
    -0.06
     léka
    -0.06
     fetish
    -0.06
     urged
    -0.06
    Mad
    -0.06
    POSITIVE LOGITS
    `)↵
    0.06
    _REPLY
    0.06
     Editorial
    0.06
    Houston
    0.06
    每
    0.06
    _samples
    0.06
     Alexand
    0.06
     рев
    0.06
     Sorted
    0.06
    keleton
    0.06
    Activations Density 0.023%

    No Known Activations