© 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. 54300
    Prev
    Next
    INDEX
    Explanations

    computing tools and features

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of “tool” or “tools,” i.e. when the text is talking about using tools (especially the token “Tool”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information related to AI tools and their functionalities.

    oai_token-act-pair · gpt-4o-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
     Verizon
    -0.06
     lời
    -0.06
    iol
    -0.06
     ""),↵
    -0.06
    Fake
    -0.06
     Shader
    -0.06
    ジェ
    -0.06
     setValue
    -0.06
     {}".
    -0.06
     Girl
    -0.06
    POSITIVE LOGITS
     LNG
    0.07
     mant
    0.07
     relates
    0.06
    骨
    0.06
    ้าส
    0.06
    oplast
    0.06
     Modified
    0.06
    :</
    0.06
    :
    0.06
    ?>"></
    0.06
    Activations Density 0.005%

    No Known Activations