© 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. 9126
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    conversations about tasks involving purchasing or checking food items.

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

    The neuron is looking for the document’s “News Article” heading or similar section-label tokens.

    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
     blade
    -0.07
    ACH
    -0.06
    Anime
    -0.06
     dysfunction
    -0.06
     تسم
    -0.06
    ,err
    -0.06
    -cal
    -0.06
     whip
    -0.06
     anom
    -0.06
     Tome
    -0.06
    POSITIVE LOGITS
    :CGRectMake
    0.07
    ↵↵↵
    0.07
    hões
    0.06
     defaultstate
    0.06
    th
    0.06
     졸업
    0.06
    ð
    0.06
    crease
    0.06
     CGRectMake
    0.06
     JFactory
    0.06
    Activations Density 0.007%

    No Known Activations