© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43192
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of loop‐initializing “for” keywords (the starts of for-loops).

    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
     Flat
    -0.07
     crimes
    -0.07
     Brennan
    -0.07
     Golf
    -0.06
     linkage
    -0.06
     Whe
    -0.06
     Gew
    -0.06
    ณฑ
    -0.06
    <{↵
    -0.06
    浴
    -0.06
    POSITIVE LOGITS
    ροφορίες
    0.07
    ๊ก
    0.06
    Sending
    0.06
    _chan
    0.06
     öner
    0.06
    持续
    0.06
     mantener
    0.06
    ryption
    0.06
    ός
    0.05
     тяжел
    0.05
    Activations Density 0.007%

    No Known Activations