© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126256
    Prev
    Next
    INDEX
    Explanations

    Research paper introductions

    np_max-act · gemini-2.0-flash

    This neuron responds to academic research–style discourse, especially method‐ and paper‐description terms common in scientific abstracts (e.g. “methods,” “propose,” “perform,” “train,” “demonstrate”).

    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
     Ста
    -0.06
    _annotation
    -0.06
    iferay
    -0.06
    .bad
    -0.06
    けない
    -0.06
     UX
    -0.06
     rozp
    -0.06
    ANY
    -0.06
    	ADD
    -0.06
    hecy
    -0.06
    POSITIVE LOGITS
     股
    0.08
     leak
    0.07
     bulky
    0.07
     Criminal
    0.06
    InputLabel
    0.06
     LOWER
    0.06
     использовать
    0.06
     khối
    0.06
    		↵
    0.06
     leggings
    0.06
    Activations Density 0.047%

    No Known Activations