© 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. 126858
    Prev
    Next
    INDEX
    Explanations

    small amounts accumulating

    np_max-act · gemini-2.0-flash

    This neuron responds to instances of additive accumulation phrasing—especially the idiomatic “add up” (and its immediate context).

    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
    -html
    -0.06
    лід
    -0.06
    xies
    -0.06
    हर
    -0.06
    สมเด
    -0.06
    focused
    -0.06
    냥
    -0.06
    .@
    -0.06
    Дж
    -0.06
    vfs
    -0.06
    POSITIVE LOGITS
     ripped
    0.07
     worthy
    0.06
    _almost
    0.06
    \"><
    0.06
     @"\
    0.06
     chtě
    0.06
    ').'</
    0.06
    /tr
    0.06
     yelling
    0.06
    visibility
    0.06
    Activations Density 0.019%

    No Known Activations