© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109752
    Prev
    Next
    INDEX
    Explanations

    names, identifiers

    np_max-act · gemini-2.0-flash

    This neuron fires on XML attribute values that look like CamelCase component or module/class 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
    Recorder
    -0.07
    357
    -0.07
     трет
    -0.07
     Clifford
    -0.07
    reements
    -0.06
    霞
    -0.06
     vests
    -0.06
     Hern
    -0.06
    .Num
    -0.06
     Rahul
    -0.06
    POSITIVE LOGITS
    patient
    0.06
    ideas
    0.06
    ivism
    0.06
    <meta
    0.06
     attempted
    0.06
    merchant
    0.06
     Navigate
    0.06
    备份
    0.06
    "/>.↵
    0.06
     CS
    0.06
    Activations Density 0.016%

    No Known Activations