© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38659
    Prev
    Next
    INDEX
    Explanations

    heart

    np_max-act · gemini-2.0-flash

    terms related to cardiac and neurological functions.

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

    The neuron activates on terms referring to heart function and cardiovascular physiology (e.g. “cardiac,” “myocardial,” “bradycardia,” baroreceptor reflex).

    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
    reste
    -0.07
    isValid
    -0.06
    ValueCollection
    -0.06
    arak
    -0.06
    .attrs
    -0.06
     Dare
    -0.06
     Robertson
    -0.06
    ialect
    -0.06
    ategorias
    -0.06
     Rachel
    -0.06
    POSITIVE LOGITS
    ους
    0.06
    UTF
    0.06
    (::
    0.06
    Ag
    0.06
     damn
    0.06
    .TRUE
    0.06
     kotlin
    0.06
    .Cons
    0.06
     exchanging
    0.06
    �
    0.06
    Activations Density 0.020%

    No Known Activations