© 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. 126063
    Prev
    Next
    INDEX
    Explanations

    business reviews

    np_max-act · gemini-2.0-flash

    This neuron detects section headings or subheadings (the titled “H2”-style lines) in instructional or list‐format texts.

    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
     ขาย
    -0.07
    .preferences
    -0.06
    Buscar
    -0.06
     wg
    -0.06
     звер
    -0.06
    ده
    -0.06
    /blog
    -0.06
    调用
    -0.06
     firefight
    -0.06
     anál
    -0.06
    POSITIVE LOGITS
    issippi
    0.07
    /support
    0.06
    540
    0.06
    _sample
    0.06
    aris
    0.06
    .Standard
    0.06
    ेत
    0.06
    ΑΜ
    0.06
     Welt
    0.06
    .getLeft
    0.06
    Activations Density 0.049%

    No Known Activations