© 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. 126087
    Prev
    Next
    INDEX
    Explanations

    Faults or defects

    np_max-act · gemini-2.0-flash

    This neuron detects numbered list markers and item identifiers (e.g., “1.”, “2.”, “STQ-SNP-STR-0003_00_Attachment #1,” etc.).

    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
     kosten
    -0.07
    Rad
    -0.07
    狗
    -0.07
     galaxies
    -0.06
    CAP
    -0.06
    	buffer
    -0.06
    PROTO
    -0.06
    adc
    -0.06
     standoff
    -0.06
     galaxy
    -0.06
    POSITIVE LOGITS
     rushed
    0.06
     SQLAlchemy
    0.06
     الآ
    0.06
    大阪
    0.06
     stole
    0.06
     özellikleri
    0.06
    anooga
    0.06
     Chattanooga
    0.06
     unrestricted
    0.06
     blitz
    0.06
    Activations Density 0.020%

    No Known Activations