© 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. 6732
    Prev
    Next
    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash

    This neuron fires on header‐and‐metadata text, i.e. tokens in post titles, bylines or URLs (including author names, titles, and link fragments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical discussions and descriptions related to web development and user interface design.

    oai_token-act-pair · gpt-4o-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
    Across
    -0.07
    _app
    -0.07
    %%%%
    -0.07
     lit
    -0.07
    river
    -0.06
     morally
    -0.06
    (Note
    -0.06
    .forward
    -0.06
    (S
    -0.06
     AB
    -0.06
    POSITIVE LOGITS
    WindowTitle
    0.07
    Ģ
    0.06
    ritel
    0.06
    itbart
    0.06
     deception
    0.06
    ubi
    0.06
     \`
    0.06
     psycopg
    0.06
     banc
    0.06
    .Extensions
    0.06
    Activations Density 0.088%

    No Known Activations