© 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. 6435
    Prev
    Next
    INDEX
    Explanations

    coupling

    np_max-act · gemini-2.0-flash

    The neuron activates on technical phrases denoting physical coupling or interaction strength (e.g. “strong coupling,” “interacting with,” “cavity QED”) in physics contexts.

    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
    _vlog
    -0.07
    _partition
    -0.06
    �
    -0.06
     خوان
    -0.06
    OCK
    -0.06
    市
    -0.06
     ALS
    -0.06
    紅
    -0.06
     наві
    -0.06
     Transcript
    -0.06
    POSITIVE LOGITS
    arence
    0.06
     nouvelle
    0.06
    часно
    0.06
    mesh
    0.06
    ification
    0.06
     suspense
    0.06
    額
    0.06
    DOCTYPE
    0.06
     embassy
    0.06
    сед
    0.06
    Activations Density 0.004%

    No Known Activations