© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89681
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash

    emojis and slang expressions that convey a casual, playful tone.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron is primarily responsive to emojis and other nonstandard Unicode symbols in the text.

    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
    rails
    -0.07
    |min
    -0.07
    ±ظ
    -0.07
    	md
    -0.07
    こそ
    -0.06
    |max
    -0.06
     باعث
    -0.06
    )<=
    -0.06
    =result
    -0.06
    .ComponentPlacement
    -0.06
    POSITIVE LOGITS
     getVersion
    0.07
     enrich
    0.07
    优
    0.06
     hom
    0.06
    347
    0.06
    receiver
    0.06
    vez
    0.06
    occup
    0.06
    мя
    0.06
     restrictive
    0.06
    Activations Density 0.001%

    No Known Activations