© 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. 126886
    Prev
    Next
    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    This neuron detects boundary markers—words signaling “end” or “after” (e.g. the token “end” in English and “后面” in Chinese).

    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
    出品者
    -0.07
    олот
    -0.07
     excludes
    -0.07
    оны
    -0.06
    Gear
    -0.06
     Walking
    -0.06
     미국
    -0.06
    forg
    -0.06
    changed
    -0.06
    itches
    -0.06
    POSITIVE LOGITS
    _tasks
    0.07
     CENT
    0.06
    _SECRET
    0.06
    :last
    0.06
    brace
    0.06
     Mazda
    0.06
    .inf
    0.06
    verbosity
    0.06
    \uC
    0.06
     contend
    0.06
    Activations Density 0.240%

    No Known Activations