© 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
    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. 7232
    Prev
    Next
    INDEX
    Explanations

    Remaining competitive in business

    np_max-act · gemini-2.0-flash

    This neuron detects recommendation or advisory language—phrases that urge taking action (e.g., “should,” “need to,” “consider,” “remain competitive”).

    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
    Ap
    -0.07
     EU
    -0.07
     today
    -0.06
     TL
    -0.06
     Jessie
    -0.06
     cał
    -0.06
    -hole
    -0.06
     cosa
    -0.06
    EK
    -0.06
    нями
    -0.06
    POSITIVE LOGITS
    dna
    0.07
    /v
    0.07
    aret
    0.07
     gains
    0.07
    .role
    0.06
    _Stream
    0.06
     remed
    0.06
    .feature
    0.06
     chapters
    0.06
    .UserInfo
    0.06
    Activations Density 0.046%

    No Known Activations