© 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. 126652
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    np_max-act · gemini-2.0-flash

    descriptions of capabilities and functionalities of an AI language model.

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

    This neuron activates on tokens that are part of the assistant’s self-descriptions or capability listings—especially the “I can…” statements and their accompanying list markers.

    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
    stroke
    -0.07
    pec
    -0.06
    _matching
    -0.06
    增加
    -0.06
    purchase
    -0.06
     MethodInvocation
    -0.06
        
    -0.06
    -width
    -0.06
     tăng
    -0.06
    mix
    -0.06
    POSITIVE LOGITS
     ScrollView
    0.07
    ])).
    0.07
     OPTIONS
    0.07
    groupBy
    0.06
     ].
    0.06
     �
    0.06
    >)
    0.06
     ze
    0.06
    —he
    0.06
     np
    0.06
    Activations Density 0.040%

    No Known Activations