© 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. 13527
    Prev
    Next
    INDEX
    Explanations

    resizing

    np_max-act · gemini-2.0-flash

    The neuron spotlights terms related to dynamic or responsive sizing and layout adjustments (e.g. responsive, resize, adjust, dynamic).

    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
    اطر
    -0.07
     attractive
    -0.07
    enze
    -0.06
     silent
    -0.06
     striped
    -0.06
     bundles
    -0.06
    _SKIP
    -0.06
     gun
    -0.06
     identifiable
    -0.06
     Kanun
    -0.06
    POSITIVE LOGITS
    玻璃
    0.07
    Courtesy
    0.06
    Sp
    0.06
    +"</
    0.06
    について
    0.06
    SERVER
    0.06
     whe
    0.06
    *",
    0.06
     조회
    0.06
     Assuming
    0.06
    Activations Density 0.013%

    No Known Activations