© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55765
    Prev
    Next
    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions that English isn’t someone’s first language (e.g. the phrase “English is not his/her first language”).

    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
    .MSG
    -0.07
    녁
    -0.06
     Miscellaneous
    -0.06
    /rand
    -0.06
    .Dispatch
    -0.06
     arcs
    -0.06
    كييف
    -0.06
    졌
    -0.06
    -unit
    -0.06
     crore
    -0.06
    POSITIVE LOGITS
    .Ptr
    0.06
     influencers
    0.06
    Via
    0.06
     Guill
    0.06
    รร
    0.06
     Reno
    0.06
    Species
    0.06
     BIOS
    0.06
     tık
    0.06
    ElementType
    0.06
    Activations Density 0.009%

    No Known Activations