© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85699
    Prev
    Next
    INDEX
    Explanations

    congestion

    np_max-act · gemini-2.0-flash

    This neuron responds to references to the nasal passages and related nasal/mucosal symptoms (e.g., “nasal,” “mucosa,” sprays, congestion, drainage).

    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
     weighs
    -0.07
     Сп
    -0.07
    ecimal
    -0.07
     Diff
    -0.07
    Her
    -0.07
     bounced
    -0.06
    ologists
    -0.06
     emulate
    -0.06
     Pit
    -0.06
    onDelete
    -0.06
    POSITIVE LOGITS
    /yyyy
    0.07
     декабря
    0.06
     recurse
    0.06
    ंपन
    0.06
     inc
    0.06
     Katrina
    0.06
     düşün
    0.06
    Wire
    0.06
    Billing
    0.06
    ์ก
    0.06
    Activations Density 0.005%

    No Known Activations