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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56612
    Prev
    Next
    INDEX
    Explanations

    external links and references

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the names and title‐like tokens that appear in page headings and external‐link labels (i.e. the article’s subject names and link titles).

    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
     RoundedRectangle
    -0.07
     Oxygen
    -0.06
    UIStoryboardSegue
    -0.06
    ahoma
    -0.06
     quarterback
    -0.06
     evacuated
    -0.06
    olated
    -0.06
     PI
    -0.06
    -com
    -0.06
    _commands
    -0.06
    POSITIVE LOGITS
     Likes
    0.07
     barring
    0.07
     náro
    0.07
    涨
    0.07
    StreamReader
    0.06
    bs
    0.06
    覺
    0.06
    届
    0.06
     обнаруж
    0.06
     مقدار
    0.06
    Activations Density 0.019%

    No Known Activations