© 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. 6813
    Prev
    Next
    INDEX
    Explanations

    NER

    np_max-act · gemini-2.0-flash

    The neuron specifically responds to mentions of Named Entity Recognition (NER) and related extraction terminology.

    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
    혀
    -0.06
    .likes
    -0.06
    	switch
    -0.06
     artificially
    -0.06
    alink
    -0.06
    DEPTH
    -0.06
    {\"
    -0.06
    ULATE
    -0.06
    лата
    -0.05
     BOOK
    -0.05
    POSITIVE LOGITS
     민
    0.07
    ffi
    0.06
    
    0.06
     výro
    0.06
    opard
    0.06
     Indices
    0.06
     těž
    0.06
     physically
    0.06
     awesome
    0.06
     raced
    0.06
    Activations Density 0.007%

    No Known Activations