© 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. 109822
    Prev
    Next
    INDEX
    Explanations

    "Unless otherwise stated"

    np_max-act · gemini-2.0-flash

    The neuron is triggered by standard legal‐oriented boilerplate beginnings, especially “Unless otherwise stated,”-style exception clauses.

    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
    لاث
    -0.07
    uada
    -0.07
    alled
    -0.06
    írk
    -0.06
     escri
    -0.06
     writes
    -0.06
     disgust
    -0.06
     garden
    -0.06
     Apartment
    -0.06
     ประเทศ
    -0.06
    POSITIVE LOGITS
    .MILLISECONDS
    0.07
     kvin
    0.06
    addItem
    0.06
    .fillText
    0.06
     ACS
    0.06
     üçüncü
    0.06
    Mode
    0.06
     YÖ
    0.06
    /social
    0.06
    交通
    0.06
    Activations Density 0.002%

    No Known Activations