© 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. 92635
    Prev
    Next
    INDEX
    Explanations

    Addresses/Buildings

    np_max-act · gemini-2.0-flash

    The neuron detects words that are part of building or venue names (e.g. “Mansion,” “Chambers,” “Centre,” “Plaza,” etc.) in an address.

    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
     melts
    -0.07
     td
    -0.07
     bezier
    -0.06
    /options
    -0.06
     nucleus
    -0.06
     Lu
    -0.06
     Exploration
    -0.06
     Harr
    -0.06
     Marg
    -0.06
    USD
    -0.06
    POSITIVE LOGITS
    áte
    0.07
     víde
    0.07
    EMY
    0.06
     『
    0.06
     plaza
    0.06
     《
    0.06
     pry
    0.06
    ädchen
    0.06
     προϊ
    0.06
     nedost
    0.06
    Activations Density 0.028%

    No Known Activations