Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 90543
    Prev
    Next
    INDEX
    Explanations

    particles

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of particulate contamination (dust, debris, particles, grime, droplets) and related sensor or clogging contexts.

    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
    _zip
    -0.07
     pour
    -0.06
     requested
    -0.06
    =set
    -0.06
    ænd
    -0.06
     Ambient
    -0.06
    σουν
    -0.06
     arrayWith
    -0.06
     buses
    -0.06
     piston
    -0.06
    POSITIVE LOGITS
     SCM
    0.07
    sik
    0.07
    KERNEL
    0.07
    errick
    0.06
    .require
    0.06
    okia
    0.06
    Harry
    0.06
    _FOCUS
    0.06
    HDATA
    0.06
     LAST
    0.06
    Activations Density 0.030%

    No Known Activations