© 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. 54107
    Prev
    Next
    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash

    The neuron flags the leading colon in Sphinx-style docstring field markers (e.g. “:param:”, “:return:”, “:raises:” etc.).

    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
    AKER
    -0.06
    bh
    -0.06
    kla
    -0.06
    ?>">↵
    -0.06
    =["
    -0.06
    (cors
    -0.06
    葉
    -0.06
    .bottom
    -0.06
    林
    -0.06
    ristol
    -0.06
    POSITIVE LOGITS
     abdomen
    0.07
     �
    0.07
    ariate
    0.07
     flaw
    0.07
     Error
    0.07
     advises
    0.07
     Brew
    0.07
     telev
    0.06
     inability
    0.06
     choisir
    0.06
    Activations Density 0.004%

    No Known Activations