© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128451
    Prev
    Next
    INDEX
    Explanations

    General English sentences

    np_max-act · gemini-2.0-flash

    The neuron responds to words that introduce or accompany quantitative details or statistics—i.e. tokens used in reporting numbers, measures, or data.

    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
     recorder
    -0.06
     icing
    -0.06
     MainActivity
    -0.06
    "No
    -0.06
    -inch
    -0.06
     victims
    -0.06
    那种
    -0.06
    .repaint
    -0.06
     PARTICULAR
    -0.05
     включ
    -0.05
    POSITIVE LOGITS
     progressed
    0.07
    ब
    0.07
    ]\
    0.07
    표
    0.07
     TD
    0.07
     starving
    0.07
    olec
    0.07
    +\
    0.07
    ok
    0.06
    find
    0.06
    Activations Density 2.353%

    No Known Activations