© 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. 110332
    Prev
    Next
    INDEX
    Explanations

    described

    np_max-act · gemini-2.0-flash

    This neuron detects formal framing phrases in patent text—especially occurrences of “shown and described” and similar introductory language.

    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
    (tolua
    -0.07
    \xaa
    -0.06
    lectric
    -0.06
    φορά
    -0.06
     Goldberg
    -0.06
    活動
    -0.06
    弱
    -0.06
     mask
    -0.06
     FLAG
    -0.06
    krom
    -0.06
    POSITIVE LOGITS
    (hist
    0.07
    ointment
    0.07
     environmentally
    0.07
    (Output
    0.06
     Patriot
    0.06
     description
    0.06
     steadfast
    0.06
     demir
    0.06
    pegawai
    0.06
     отказ
    0.06
    Activations Density 0.012%

    No Known Activations