© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109448
    Prev
    Next
    INDEX
    Explanations

    industrial processes

    np_max-act · gemini-2.0-flash

    This neuron responds to specialized technical process and material terms (e.g., chemical processes, diffusion/bonding methods, specific solvents or materials) used in engineering and industrial 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
    鋼
    -0.06
    กต
    -0.06
    idth
    -0.06
    a
    -0.06
     thrive
    -0.06
     Jose
    -0.06
    主
    -0.06
    On
    -0.06
     Charleston
    -0.06
     проз
    -0.06
    POSITIVE LOGITS
    	cerr
    0.06
    ियम
    0.06
     ATP
    0.06
    astle
    0.06
    oire
    0.06
    -remove
    0.06
    peon
    0.06
     stati
    0.06
    Detalle
    0.06
    getStyle
    0.06
    Activations Density 0.064%

    No Known Activations