© 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. 109792
    Prev
    Next
    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting research-proposal language, such as terms like “proposed,” “research,” “project,” or other project-summary and aims headings.

    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
    _APPRO
    -0.07
     autop
    -0.06
    rollment
    -0.06
    .nama
    -0.06
    くる
    -0.06
     Audit
    -0.06
    _birth
    -0.06
     Alarm
    -0.06
    ikhail
    -0.06
    할
    -0.06
    POSITIVE LOGITS
     Murray
    0.07
    講
    0.06
     kraj
    0.06
     phenomen
    0.06
     Çağ
    0.06
     transmission
    0.06
     Mountain
    0.06
    آخر
    0.06
     В
    0.06
     fotoğraf
    0.06
    Activations Density 0.012%

    No Known Activations