© 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. 128885
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash

    The neuron fires on conversational first‐/second‐person filler phrases—especially “I don’t know about you, but…”‐style asides and direct addresses to the reader.

    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
     ти
    -0.07
    790
    -0.06
    Tbl
    -0.06
     Cosby
    -0.06
    hack
    -0.06
     judge
    -0.06
     Amp
    -0.06
    ipelines
    -0.06
     Wal
    -0.06
     RT
    -0.06
    POSITIVE LOGITS
     situación
    0.07
     cambi
    0.07
     hostility
    0.06
     synchron
    0.06
    reply
    0.06
     Chart
    0.06
    .onOptionsItemSelected
    0.06
    不同
    0.06
    ’ят
    0.06
    .getLine
    0.06
    Activations Density 0.061%

    No Known Activations