© 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. 57187
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens used as list or counter indices (i.e. the digits marking positions in a counted list).

    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
    -decoration
    -0.06
     ();
↵
    -0.06
     обуч
    -0.06
    ［
    -0.06
    (epoch
    -0.06
     ers
    -0.06
     Dependencies
    -0.06
    _pe
    -0.06
    Radians
    -0.06
     artış
    -0.06
    POSITIVE LOGITS
    ]=>
    0.08
    ivo
    0.07
     Experts
    0.06
    hy
    0.06
    Dispatch
    0.06
     المخت
    0.06
    "http
    0.06
    ınca
    0.06
    ὸ
    0.06
    âr
    0.06
    Activations Density 0.014%

    No Known Activations