Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 129080
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron is strongly activated by scholarly study or paper titles (i.e. multi‐word titles often enclosed in quotation marks).

    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
     SD
    -0.07
     CIM
    -0.07
     при
    -0.06
    Algorithm
    -0.06
    visualization
    -0.06
    Lab
    -0.06
     KH
    -0.06
    594
    -0.06
     {
    ↵
    ↵
    -0.06
     с
    -0.06
    POSITIVE LOGITS
     무슨
    0.07
     tslint
    0.07
     Undefined
    0.07
     zdravot
    0.07
     tyto
    0.07
     componentDid
    0.06
    歲
    0.06
     визнач
    0.06
    ское
    0.06
     rencontre
    0.06
    Activations Density 0.054%

    No Known Activations