© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6385
    Prev
    Next
    INDEX
    Explanations

    code and game environments

    np_max-act · gemini-2.0-flash

    references to gaming environments and character mechanics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects references to spatial locations, room names, and movement/navigation cues.

    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
    -mult
    -0.07
    -home
    -0.07
     تد
    -0.07
    Як
    -0.07
     tet
    -0.07
    ijing
    -0.07
     ′
    -0.06
    ظ
    -0.06
    _ENV
    -0.06
    reuse
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵
    0.08
     نویس
    0.06
    .Job
    0.06
    hora
    0.06
     replied
    0.06
    .gridx
    0.06
     \↵↵
    0.06
     Alex
    0.06
    _RATIO
    0.06
    (items
    0.06
    Activations Density 0.005%

    No Known Activations