© 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. 45033
    Prev
    Next
    INDEX
    Explanations

    reflex

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on references to the baroreceptor reflex (baroreflex) and related reflex-control terminology.

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

    terms related to cardiovascular function and regulation, particularly in relation to blood pressure.

    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
    _adc
    -0.07
     projectiles
    -0.07
    	pstmt
    -0.07
    attack
    -0.07
    voje
    -0.07
    _atoms
    -0.07
    .List
    -0.06
     frags
    -0.06
     vur
    -0.06
    070
    -0.06
    POSITIVE LOGITS
     retrofit
    0.06
     Nom
    0.06
     há
    0.06
    lake
    0.06
     dangling
    0.06
     Mounted
    0.06
    _execute
    0.06
     yu
    0.06
    ा↵↵
    0.05
    规
    0.05
    Activations Density 0.007%

    No Known Activations