© 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. 126094
    Prev
    Next
    INDEX
    Explanations

    steps in a process

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of procedural step introductions (phrases like “the first step,” “the next step,” “the final step,” etc.) in multi‐stage process descriptions.

    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
    decimal
    -0.07
     Operand
    -0.07
     choir
    -0.07
     FLAG
    -0.06
     bandwidth
    -0.06
    Born
    -0.06
    upd
    -0.06
     亚洲
    -0.06
     banker
    -0.06
     UserRole
    -0.06
    POSITIVE LOGITS
    /Common
    0.07
     AtomicInteger
    0.06
    まで
    0.06
    _Main
    0.06
    ","+
    0.06
    .nan
    0.06
    (Main
    0.06
     cmb
    0.06
    .createSequentialGroup
    0.06
    Adjacent
    0.06
    Activations Density 0.040%

    No Known Activations