© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126203
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    terms related to patient outcomes and medical studies.

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

    The neuron responds to the indefinite article “a” when it introduces an academic study type (e.g. “a retrospective…,” “a pilot study,” “a meta-analysis,” etc.).

    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
    الى
    -0.07
    비
    -0.07
    Hillary
    -0.06
     Allah
    -0.06
     junk
    -0.06
    ुपए
    -0.06
    _EOF
    -0.06
    Ever
    -0.06
    SRC
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     compliance
    0.07
     Morrow
    0.07
    &e
    0.07
    ,'
    0.06
     Wordpress
    0.06
     %(
    0.06
    AndHashCode
    0.06
     füh
    0.06
     +#+
    0.06
     deploy
    0.06
    Activations Density 0.009%

    No Known Activations