Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 130497
    Prev
    Next
    INDEX
    Explanations

    cooking eggs and flipping

    np_max-act · gemini-2.0-flash

    This neuron activates on the special model “header” tokens that mark the start of a speaker or section (e.g. `<|start_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
     Infantry
    -0.07
    Recorder
    -0.07
    'use
    -0.07
     imped
    -0.06
     zor
    -0.06
    анні
    -0.06
    .putString
    -0.06
     clique
    -0.06
    	free
    -0.06
     Пот
    -0.06
    POSITIVE LOGITS
     ambitious
    0.07
    rais
    0.07
    Lie
    0.06
    udson
    0.06
    undreds
    0.06
    (Symbol
    0.06
     disag
    0.06
    하기
    0.06
     Employment
    0.06
    (baseUrl
    0.06
    Activations Density 0.009%

    No Known Activations