© 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. 916
    Prev
    Next
    INDEX
    Explanations

    Descriptions of usage

    np_max-act · gemini-2.0-flash

    The neuron triggers on words that introduce examples or categories—e.g. “such,” “as,” “for,” “or”—marking list-leading or example-introducing phrases.

    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
    重複重複
    -0.06
    91
    -0.06
    ilinx
    -0.06
     mixer
    -0.06
     constraints
    -0.06
    .Unicode
    -0.06
     elected
    -0.06
    .email
    -0.06
    omething
    -0.06
     angled
    -0.05
    POSITIVE LOGITS
     прим
    0.07
    ปร
    0.06
    .cent
    0.06
     bás
    0.06
     rửa
    0.06
     negot
    0.06
    اذا
    0.06
     robber
    0.06
    缩
    0.06
     가까
    0.06
    Activations Density 0.055%

    No Known Activations