© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7759
    Prev
    Next
    INDEX
    Explanations

    Item

    np_max-act · gemini-2.0-flash

    The neuron is selectively activating on HTML class‐attribute tokens—especially hyphenated CSS/Bootstrap utility class names.

    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
     embedding
    -0.07
     bombard
    -0.06
     Django
    -0.06
    券
    -0.06
     quarter
    -0.06
    ":""
    -0.06
    難
    -0.06
     MIX
    -0.06
     Erf
    -0.06
     Mand
    -0.06
    POSITIVE LOGITS
    으
    0.06
    [next
    0.06
    �
    0.06
    _LOG
    0.06
    子
    0.06
    तर
    0.06
     herbs
    0.06
    -LAST
    0.06
    Optional
    0.06
    (笑
    0.06
    Activations Density 0.013%

    No Known Activations