© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12385
    Prev
    Next
    INDEX
    Explanations

    computer network communication

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric latency measurements (floating-point round-trip times, e.g. “0.347 ms”) in traceroute/ping outputs.

    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
     utilise
    -0.06
     detained
    -0.06
     valleys
    -0.06
    かない
    -0.06
    .dirname
    -0.06
    Locker
    -0.05
    Bind
    -0.05
     što
    -0.05
    .putString
    -0.05
    724
    -0.05
    POSITIVE LOGITS
    career
    0.06
     mortgage
    0.06
     ㅇ
    0.06
     Campus
    0.06
    _PRIORITY
    0.06
    charm
    0.06
    ㅇ
    0.06
     touchdowns
    0.06
    agues
    0.06
    	progress
    0.06
    Activations Density 0.006%

    No Known Activations