© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 124839
    Prev
    Next
    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash

    The neuron activates on mask‐filling cues—specifically the “[”, “MASK”, and related bracket tokens used to indicate fill‐in‐the‐blank positions.

    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
    ひと
    -0.07
     groups
    -0.07
    Think
    -0.07
    Browsable
    -0.07
    Await
    -0.07
    encoding
    -0.06
     convin
    -0.06
    CanBe
    -0.06
     languages
    -0.06
     comparator
    -0.06
    POSITIVE LOGITS
    ساس
    0.07
     जनत
    0.06
     MotionEvent
    0.06
    ProgressHUD
    0.06
     ypos
    0.06
     euros
    0.06
    ("#
    0.06
    ostringstream
    0.06
    км
    0.06
    uably
    0.05
    Activations Density 0.006%

    No Known Activations