© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130147
    Prev
    Next
    INDEX
    Explanations

    mentions and references

    np_max-act · gemini-2.0-flash

    This neuron fires on meta-linguistic words that talk about referencing or mentioning content (e.g. “mention,” “refer,” “include”).

    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
     minutos
    -0.07
     blush
    -0.07
     рабо
    -0.06
     Пет
    -0.06
     mobile
    -0.06
     shaving
    -0.06
    سات
    -0.06
     Hurt
    -0.06
    Ke
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     نشان
    0.06
     PM
    0.06
    OrNil
    0.06
    (stat
    0.06
    fragistics
    0.06
     Trần
    0.06
    (TreeNode
    0.06
     stylesheet
    0.06
    ข
    0.06
    Parking
    0.06
    Activations Density 0.022%

    No Known Activations