© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7126
    Prev
    Next
    INDEX
    Explanations

    Chemical purification process

    np_max-act · gemini-2.0-flash

    The neuron flags terms describing chemical‐processing actions—especially purification and isolation steps (e.g. filtering, drying, crystallizing, extracting).

    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
     PUS
    -0.06
     BaseType
    -0.06
     TPM
    -0.06
    ーデ
    -0.06
     Damascus
    -0.06
    олее
    -0.06
    .pretty
    -0.06
     Sessions
    -0.06
     kitap
    -0.06
     مؤ
    -0.06
    POSITIVE LOGITS
    阪
    0.06
     nike
    0.06
     cornerback
    0.06
     같습니다
    0.06
     almond
    0.06
     assort
    0.06
    .equal
    0.06
    ังกฤษ
    0.05
     srand
    0.05
    Network
    0.05
    Activations Density 0.025%

    No Known Activations