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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13575
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron fires on definitional or introductory clauses in technical writing—e.g. sentences of the form “X is Y” or stating the study’s aim.

    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
     ethereum
    -0.07
     Frauen
    -0.07
    -seat
    -0.07
    美國
    -0.06
    -wheel
    -0.06
    нием
    -0.06
    /name
    -0.06
    pond
    -0.06
                                                                          
    -0.06
    /ml
    -0.06
    POSITIVE LOGITS
    )、
    0.07
    .Deserialize
    0.06
     slightly
    0.06
     DEBUG
    0.06
     CONTEXT
    0.06
    impl
    0.06
    <main
    0.06
     dost
    0.06
     прин
    0.06
    QDebug
    0.06
    Activations Density 0.408%

    No Known Activations