© 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. 8742
    Prev
    Next
    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash

    This neuron broadly signals the presence of any non‐punctuation token, activating (to varying degrees) on essentially every word.

    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
     dragons
    -0.07
    LEVEL
    -0.06
    _value
    -0.06
    يز
    -0.06
     У
    -0.06
    banks
    -0.06
    Japan
    -0.06
    으면
    -0.06
     Jenner
    -0.06
    ά
    -0.06
    POSITIVE LOGITS
    .cam
    0.06
     frameborder
    0.06
    �
    0.06
    problems
    0.06
    getProperty
    0.06
     Wiki
    0.06
    оратив
    0.06
     --↵
    0.06
     gratuita
    0.06
    _environment
    0.06
    Activations Density 0.024%

    No Known Activations