© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12965
    Prev
    Next
    INDEX
    Explanations

    Descriptive adjectives

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens involved in listing or enumerating items—words that introduce or label elements in a list or table.

    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
    _large
    -0.07
    uja
    -0.06
    -scalable
    -0.06
    .Headers
    -0.06
    implementation
    -0.06
     Eventually
    -0.06
     Sam
    -0.06
    NSError
    -0.06
    .reporting
    -0.06
     Dawn
    -0.06
    POSITIVE LOGITS
    �
    0.07
     arenas
    0.07
    webElementXpaths
    0.06
    чески
    0.06
    џџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџ
    0.06
     indis
    0.06
     يع
    0.06
    ').'</
    0.06
    :UI
    0.06
    useRalative
    0.06
    Activations Density 0.614%

    No Known Activations