© 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. 89290
    Prev
    Next
    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash

    This neuron detects the initial word of a sentence or section (often a single capitalized token like “The,” “We,” or “A”) in legal‐style text.

    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
    statt
    -0.07
     Rs
    -0.06
     bern
    -0.06
    gtest
    -0.06
    )");↵↵
    -0.06
     오후
    -0.06
    bbc
    -0.06
     mile
    -0.06
    etu
    -0.06
    	dp
    -0.06
    POSITIVE LOGITS
     Montgomery
    0.07
     Orientation
    0.07
    _cases
    0.07
    .cent
    0.07
    ExecutionContext
    0.07
    .ResumeLayout
    0.06
     klik
    0.06
     gelmiş
    0.06
     Chicago
    0.06
     nylon
    0.06
    Activations Density 0.016%

    No Known Activations