© 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. 129600
    Prev
    Next
    INDEX
    Explanations

    code/logs

    np_max-act · gemini-2.0-flash

    This neuron lights up on tokens that contain uppercase letters—e.g. class, component, or XML/namespace identifiers.

    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
     Nep
    -0.07
    oving
    -0.07
    Ev
    -0.06
    vip
    -0.06
    at
    -0.06
     Rox
    -0.06
     pulver
    -0.06
     án
    -0.06
     神马收录
    -0.06
     Eph
    -0.06
    POSITIVE LOGITS
    таб
    0.07
    avig
    0.06
     kỷ
    0.06
    .SQLException
    0.06
    bitset
    0.06
     сильно
    0.06
    "bytes
    0.06
    .Multi
    0.06
    gorithms
    0.06
     hız
    0.06
    Activations Density 0.165%

    No Known Activations