© 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. 43358
    Prev
    Next
    INDEX
    Explanations

    Period punctuation

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on site‐template boilerplate and interface labels (e.g. browser‐support notices, “support the following browsers:”, pricing disclosures, and other UI metadata text).

    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
    _ass
    -0.07
     vyvol
    -0.07
    .InputStream
    -0.07
    .Signal
    -0.07
    乱
    -0.07
     پل
    -0.06
    atör
    -0.06
     aluminum
    -0.06
    ?>
↵
↵
    -0.06
    (action
    -0.06
    POSITIVE LOGITS
    itech
    0.06
    STONE
    0.06
     acidity
    0.06
     Прот
    0.06
    Disallow
    0.06
    AYOUT
    0.06
    ycopg
    0.06
    ITUDE
    0.06
     Appointment
    0.06
    Implemented
    0.06
    Activations Density 0.008%

    No Known Activations