© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128766
    Prev
    Next
    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash

    The neuron detects floating-point numeric literals (numbers containing a decimal point) in code or SVG path 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
     ALS
    -0.07
    uses
    -0.06
    _us
    -0.06
     D
    -0.06
     reached
    -0.06
    ساب
    -0.06
    erner
    -0.05
     tier
    -0.05
    ेग
    -0.05
    ersistence
    -0.05
    POSITIVE LOGITS
    -profile
    0.07
    +(
    0.06
    обходим
    0.06
     inFile
    0.06
    blick
    0.06
     هذه
    0.06
    .classList
    0.06
     организа
    0.06
     boils
    0.06
     austerity
    0.06
    Activations Density 0.002%

    No Known Activations