© 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. 92429
    Prev
    Next
    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash

    This neuron detects scientific paper section headings (e.g. “Experimental,” “Crystal data,” and other numbered section titles).

    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
     Auction
    -0.07
    .getParam
    -0.07
    ei
    -0.06
    ollywood
    -0.06
     вул
    -0.06
    master
    -0.06
    Story
    -0.06
    чин
    -0.06
     pathlib
    -0.06
    زان
    -0.06
    POSITIVE LOGITS
    _HW
    0.06
    лючается
    0.06
     بالق
    0.06
    		       
    0.06
    FORMAT
    0.06
    ../../
    0.06
     líder
    0.06
     postupně
    0.06
    LOTS
    0.06
     �
    0.06
    Activations Density 0.016%

    No Known Activations