© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128607
    Prev
    Next
    INDEX
    Explanations

    provided

    np_max-act · gemini-2.0-flash

    The neuron fires on the term “provided” in software license disclaimers (e.g. the “IS PROVIDED … BY…” phrase).

    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
     FIRE
    -0.06
    -syntax
    -0.06
     nails
    -0.06
    "We
    -0.06
     corres
    -0.06
    룡
    -0.06
    iram
    -0.06
    isans
    -0.06
     weights
    -0.06
     铁
    -0.06
    POSITIVE LOGITS
     PROVIDED
    0.09
     positively
    0.07
    acerb
    0.07
     Melbourne
    0.07
    kv
    0.07
    Created
    0.06
     provided
    0.06
    ्षक
    0.06
    prev
    0.06
    kest
    0.06
    Activations Density 0.001%

    No Known Activations