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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 69008
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    This neuron detects geographic location and directional terms that describe where places lie or how they relate spatially.

    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
    区
    -0.07
    _sms
    -0.07
     singled
    -0.06
    /output
    -0.06
    ulas
    -0.06
    identify
    -0.06
    导
    -0.06
    ictory
    -0.06
    )
    ↵
    ↵
    -0.06
     Stard
    -0.06
    POSITIVE LOGITS
     през
    0.08
    gender
    0.07
     flourish
    0.07
    陷
    0.07
    pour
    0.07
    �
    0.07
    (steps
    0.07
    ồng
    0.06
    (withId
    0.06
    玄
    0.06
    Activations Density 0.023%

    No Known Activations