© 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. 45114
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    The neuron activates on terms that describe online distribution and engagement metrics—e.g. “views,” “viral,” “premiered,” “published,” “available,” and similar words indicating audience reach or release status.

    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
    Thank
    -0.07
    tokenizer
    -0.06
    706
    -0.06
    ICT
    -0.06
    ιθ
    -0.06
    thank
    -0.06
     زمان
    -0.06
    Як
    -0.06
    technical
    -0.06
     trif
    -0.06
    POSITIVE LOGITS
    finder
    0.08
    _category
    0.07
     assist
    0.07
    .loggedIn
    0.06
     언제
    0.06
    /Error
    0.06
     NSArray
    0.06
    nodiscard
    0.06
     ListItem
    0.06
    .setEditable
    0.06
    Activations Density 0.049%

    No Known Activations