© 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. 90653
    Prev
    Next
    INDEX
    Explanations

    interfere

    np_max-act · gemini-2.0-flash

    The neuron detects technical terms referring to wave-optical phenomena (diffraction and interference).

    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
     ultimo
    -0.08
    he
    -0.07
    Items
    -0.07
    utra
    -0.07
     map
    -0.07
     lesser
    -0.07
    ysa
    -0.07
    кут
    -0.07
    _filt
    -0.06
    .layouts
    -0.06
    POSITIVE LOGITS
     Represent
    0.06
    روع
    0.06
    سة
    0.06
    	RTDBG
    0.06
     didFinish
    0.06
    illos
    0.06
    marine
    0.06
     temsil
    0.05
     supplementary
    0.05
    .Company
    0.05
    Activations Density 0.004%

    No Known Activations