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. 43584
    Prev
    Next
    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash

    This neuron selectively lights up on technical biochemical assay language—terms describing enzymes, substrates, kinetics, and experimental effect measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    mechanisms related to calcium and phosphate transport in biological systems.

    oai_token-act-pair · gpt-4o-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
     россий
    -0.06
     Prevention
    -0.06
    ヤ
    -0.06
    -tw
    -0.06
     soccer
    -0.06
     защиты
    -0.06
    academic
    -0.06
    —which
    -0.06
     wellbeing
    -0.06
     tells
    -0.06
    POSITIVE LOGITS
    (ns
    0.07
    pac
    0.06
    \Object
    0.06
    _Move
    0.06
    ;//
    0.06
    =text
    0.06
    (script
    0.06
     mang
    0.06
    	die
    0.06
    اشة
    0.06
    Activations Density 0.063%

    No Known Activations