© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125928
    Prev
    Next
    INDEX
    Explanations

    EN

    np_max-act · gemini-2.0-flash

    This neuron activates on the “EN” language/designator token in HTML/XML DOCTYPE declarations.

    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
     Equivalent
    -0.07
     مقدار
    -0.07
    ￣￣￣
    -0.07
    aja
    -0.06
     수가
    -0.06
    _car
    -0.06
     Restrictions
    -0.06
    اسر
    -0.06
    enguins
    -0.06
    icable
    -0.06
    POSITIVE LOGITS
    _checkpoint
    0.08
     moderately
    0.07
    Remove
    0.06
    SP
    0.06
     filme
    0.06
    وا
    0.06
     conscient
    0.06
     vault
    0.06
     sp
    0.06
    Clone
    0.06
    Activations Density 0.000%

    No Known Activations