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

    Neuronpedia

    Jacobian LensNEW
    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. 38907
    Prev
    Next
    INDEX
    Explanations

    influencer

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the term “influencer” (especially in “influencer marketing”).

    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
     Dart
    -0.07
    ichtet
    -0.07
    ájem
    -0.06
    forcements
    -0.06
    _rb
    -0.06
     rew
    -0.06
     Mate
    -0.06
     Commands
    -0.06
    xes
    -0.06
    _lm
    -0.06
    POSITIVE LOGITS
     influencers
    0.08
    _CB
    0.07
    先
    0.06
    越
    0.06
     Comment
    0.06
     Icon
    0.06
    .State
    0.06
    Honestly
    0.06
    129
    0.06
    uely
    0.06
    Activations Density 0.006%

    No Known Activations