© 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. 73750
    Prev
    Next
    INDEX
    Explanations

    clock

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of clock-related circuitry and timing elements (e.g. “clock,” “phase-locked,” “delay-locked,” “retiming,” “synchronous”) in technical 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
    statement
    -0.06
     Found
    -0.06
    Transactions
    -0.06
     Charges
    -0.06
    集合
    -0.06
     Mineral
    -0.06
    .mx
    -0.06
    _cd
    -0.06
     Hal
    -0.06
     artists
    -0.06
    POSITIVE LOGITS
    _strerror
    0.08
     rethink
    0.07
    mmm
    0.07
     blessings
    0.07
    dent
    0.07
    (raw
    0.06
    	gl
    0.06
     instruction
    0.06
     pace
    0.06
     heartbeat
    0.06
    Activations Density 0.009%

    No Known Activations