© 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. 43307
    Prev
    Next
    INDEX
    Explanations

    Scot

    np_max-act · gemini-2.0-flash

    The neuron activates on words or word fragments referring to “Scot” (Scotland/Scottish) such as “Scot,” “Scotia,” or “Scottish.”

    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
     UPPER
    -0.07
     Upper
    -0.07
     dip
    -0.07
    луги
    -0.07
     นาง
    -0.07
    	delta
    -0.07
     HOH
    -0.07
     dayan
    -0.07
    ategorized
    -0.06
     Hayes
    -0.06
    POSITIVE LOGITS
     Scott
    0.13
    Scott
    0.11
     sc
    0.10
     Sc
    0.10
     SC
    0.10
    sci
    0.09
    SC
    0.09
    (sc
    0.08
    Sc
    0.08
     scams
    0.08
    Activations Density 0.048%

    No Known Activations