© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30676
    Prev
    Next
    INDEX
    Explanations

    Manufacturer's instructions

    np_max-act · gemini-2.0-flash

    The neuron detects instruction-related terms and mentions of guidelines (e.g. “instructor’s,” “guidelines,” “instructions,” “follow,” “check,” “ensure”) in the text.

    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
    <count
    -0.07
     Holocaust
    -0.06
     Chronicle
    -0.06
    под
    -0.06
     IsValid
    -0.06
    -font
    -0.06
    avail
    -0.06
     pad
    -0.06
    Gener
    -0.06
    Spl
    -0.06
    POSITIVE LOGITS
    DialogContent
    0.07
    北京
    0.07
    ¥
    0.07
    .savefig
    0.06
    эф
    0.06
     expectations
    0.06
    		      
    0.06
     Poland
    0.06
    Url
    0.06
     х
    0.06
    Activations Density 0.024%

    No Known Activations