© 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. 125137
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS code

    np_max-act · gemini-2.0-flash

    The neuron responds to HTML element tag syntax—specifically the angle‐bracket delimiters (“<” and “>”) and tag names like “div” and “class.”

    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
     ontology
    -0.06
     α
    -0.06
     South
    -0.06
    .vocab
    -0.06
    -hand
    -0.06
    ’nin
    -0.06
    otted
    -0.06
    .push
    -0.06
    ibile
    -0.06
    South
    -0.06
    POSITIVE LOGITS
    най
    0.07
    raquo
    0.07
    عم
    0.06
     قص
    0.06
    나요
    0.06
    DebugEnabled
    0.06
    [iVar
    0.06
     přibliž
    0.06
    igidBody
    0.06
    ····
    0.06
    Activations Density 0.028%

    No Known Activations