© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30651
    Prev
    Next
    INDEX
    Explanations

    impressive

    np_max-act · gemini-2.0-flash

    The neuron activates on strong positive appraisal adjectives—most notably “impressive.”

    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
     Darwin
    -0.07
    water
    -0.06
     caregiver
    -0.06
     camino
    -0.06
     starvation
    -0.06
     Buk
    -0.06
     nurt
    -0.06
     Calder
    -0.06
     Biol
    -0.06
    NodeId
    -0.06
    POSITIVE LOGITS
     impressive
    0.17
     impressed
    0.11
     impress
    0.09
    Imp
    0.09
     Imp
    0.09
     IMP
    0.09
     Impress
    0.08
     impression
    0.08
     impressions
    0.08
    p
    0.07
    Activations Density 0.006%

    No Known Activations