© 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 EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 43798
    Prev
    Next
    INDEX
    Explanations

    Contractions

    np_max-act · gemini-2.0-flash

    The neuron detects apostrophe-based clitic contractions (shortened auxiliary/pronominal endings).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    耶
    -0.07
     Booth
    -0.06
    ambda
    -0.06
     potassium
    -0.06
     concatenated
    -0.06
     ethers
    -0.06
     invariant
    -0.06
     asynchronous
    -0.06
     ++)↵
    -0.06
     associ
    -0.06
    POSITIVE LOGITS
    're
    0.14
    'll
    0.13
    ’re
    0.13
    's
    0.13
    ’ll
    0.12
    'd
    0.11
    'm
    0.11
    ’s
    0.10
    'S
    0.10
    ’d
    0.10
    Activations Density 0.281%

    No Known Activations