© 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. 128740
    Prev
    Next
    INDEX
    Explanations

    research methods/properties

    np_max-act · gemini-2.0-flash

    medical and scientific terminology related to pesticides and their effects on health.

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

    This neuron activates on general scientific or experimental terms that denote methods, conditions, or influencing factors.

    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
    YLE
    -0.07
     Finger
    -0.07
     ^↵
    -0.07
     Series
    -0.06
    ogen
    -0.06
     الدولة
    -0.06
     winners
    -0.06
     hộp
    -0.06
     bathing
    -0.06
     Tor
    -0.06
    POSITIVE LOGITS
    ’il
    0.06
     व
    0.06
    _yaw
    0.06
    |unique
    0.06
    .UUID
    0.06
    ッド
    0.06
    eax
    0.06
    _atual
    0.06
    angs
    0.06
     stol
    0.06
    Activations Density 0.151%

    No Known Activations