© 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
    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. 22930
    Prev
    Next
    INDEX
    Explanations

    programming questions and answers

    np_max-act · gemini-2.0-flash

    Mentions of version-control branch and commit operations or branch-state problems (e.g., pushing, reverting, wrong/bad branch situations).

    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_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
     hott
    -0.07
    =false
    -0.06
     Gol
    -0.06
     doz
    -0.06
    anol
    -0.06
     منذ
    -0.06
     �
    -0.06
    初
    -0.06
     DialogResult
    -0.06
     objectively
    -0.06
    POSITIVE LOGITS
    Canceled
    0.07
     fost
    0.06
    _UNKNOWN
    0.06
     imgs
    0.06
    (be
    0.06
    SError
    0.06
    .payment
    0.06
     понима
    0.06
     استفاده
    0.06
    يون
    0.06
    Activations Density 0.033%

    No Known Activations