© 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. 54040
    Prev
    Next
    INDEX
    Explanations

    names and locations

    np_max-act · gemini-2.0-flash

    This neuron detects proper names of people (typically speaker or attribution names) in news‐style text.

    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
    _All
    -0.07
     معرفی
    -0.06
    toBeDefined
    -0.06
     ++;↵
    -0.06
    聘
    -0.06
     Ι
    -0.06
    [maxn
    -0.06
    ")){↵
    -0.06
    ]));
    ↵
    -0.06
    圳
    -0.06
    POSITIVE LOGITS
    يس
    0.07
    .strftime
    0.06
     Kitchen
    0.06
    uraa
    0.06
    .pattern
    0.06
     (.
    0.06
    pak
    0.06
    TRUE
    0.06
     witnessing
    0.06
     monarch
    0.06
    Activations Density 0.028%

    No Known Activations