Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 130544
    Prev
    Next
    INDEX
    Explanations

    geographic locations

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of island names.

    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
    (IntPtr
    -0.07
    ulled
    -0.07
     женщина
    -0.07
    gunta
    -0.07
    .timer
    -0.06
    (vec
    -0.06
    ้องน
    -0.06
     Instance
    -0.06
    전히
    -0.06
    ्तन
    -0.06
    POSITIVE LOGITS
     Island
    0.07
    Prop
    0.06
     Vous
    0.06
    onec
    0.06
     sost
    0.06
     Milano
    0.06
    =session
    0.06
    bytes
    0.06
    aho
    0.06
     고려
    0.06
    Activations Density 0.040%

    No Known Activations