© 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. 7-RESID-POST-AA
    6. 98069
    Prev
    Next
    INDEX
    Explanations

    ____

    np_max-act · gemini-2.0-flash

    The neuron detects long separator or formatting lines composed of repeated punctuation/underscore characters used as section dividers.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     había
    -0.06
    itate
    -0.06
    URT
    -0.06
     viewing
    -0.06
    irie
    -0.06
    Parts
    -0.06
    оз
    -0.06
     مست
    -0.06
    agy
    -0.06
    涉
    -0.06
    POSITIVE LOGITS
     Weight
    0.08
     Clothes
    0.07
     Columbus
    0.07
    152
    0.07
    chrono
    0.07
     ```
    0.07
    _VIEW
    0.07
    .fac
    0.06
     Timestamp
    0.06
    .StoredProcedure
    0.06
    Activations Density 0.001%

    No Known Activations