© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38991
    Prev
    Next
    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash

    This neuron never activates (all its activation values are zero), i.e. it doesn’t detect any pattern in the 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
    bounce
    -0.07
    -ser
    -0.06
     Coupon
    -0.06
    |l
    -0.06
    .scal
    -0.06
    ...)
    -0.06
     vacant
    -0.06
     RouterModule
    -0.06
     зовніш
    -0.06
     aligned
    -0.06
    POSITIVE LOGITS
    ARGV
    0.07
    .GET
    0.06
    "};↵↵
    0.06
     "["
    0.06
    label
    0.06
    Magn
    0.06
    upport
    0.06
    .Put
    0.06
    Ctx
    0.06
    ність
    0.06
    Activations Density 0.061%

    No Known Activations