© 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. 126734
    Prev
    Next
    INDEX
    Explanations

    Dispersion through small openings

    np_max-act · gemini-2.0-flash

    technical terms and phrases related to manufacturing processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of spray or dispersion hardware components (e.g. nozzles, atomizers, orifices, spargers).

    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
    (ch
    -0.06
     SCRIPT
    -0.06
    -yellow
    -0.06
     Moose
    -0.06
     concentration
    -0.06
     AQ
    -0.06
     bude
    -0.06
    anki
    -0.06
    rtl
    -0.06
     c
    -0.06
    POSITIVE LOGITS
     consequ
    0.06
    '',
    0.06
     Elevated
    0.06
    違
    0.06
    employer
    0.06
    yling
    0.06
     Farmers
    0.06
     anterior
    0.06
    .getvalue
    0.06
     OnDestroy
    0.06
    Activations Density 0.030%

    No Known Activations