© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6350
    Prev
    Next
    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash

    The neuron activates on instances of the words “confirm” and “deny,” as in the stock “neither confirm nor deny” refusal construction.

    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
    ungeon
    -0.07
     Yours
    -0.06
     корист
    -0.06
     maintenant
    -0.06
    (dictionary
    -0.06
     sním
    -0.06
    Suppress
    -0.06
    EDIATEK
    -0.05
    SmartPointer
    -0.05
     muz
    -0.05
    POSITIVE LOGITS
    .xpath
    0.07
    itest
    0.07
     сохран
    0.06
     Become
    0.06
     тяжел
    0.06
    mesini
    0.06
    <View
    0.06
     complain
    0.06
     posed
    0.06
     impecc
    0.06
    Activations Density 0.099%

    No Known Activations