© 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. 92098
    Prev
    Next
    INDEX
    Explanations

    online chat/forums

    np_max-act · gemini-2.0-flash

    responses related to the capabilities and functionalities of an AI language model.

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

    This neuron detects the special chat-format header boundary tokens (e.g. “<|end_header_id|>”).

    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
    ployment
    -0.07
    ToOne
    -0.06
     sphere
    -0.06
    ById
    -0.06
    	then
    -0.06
    _replace
    -0.06
     πρά
    -0.06
     "+"
    -0.06
    <M
    -0.06
    Registration
    -0.06
    POSITIVE LOGITS
    ành
    0.07
     Consum
    0.06
     έ
    0.06
     Chester
    0.06
    Fab
    0.06
     Establish
    0.06
     thro
    0.06
    おり
    0.06
    Utc
    0.06
     could
    0.06
    Activations Density 0.119%

    No Known Activations