© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59241
    Prev
    Next
    INDEX
    Explanations

    different

    np_max-act · gemini-2.0-flash

    This neuron fires on the phrase “types of,” i.e. it detects generic “types of …” constructions.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ð
    -0.06
     ส
    -0.06
     �
    -0.06
     prec
    -0.06
    agi
    -0.06
     �
    -0.06
     nob
    -0.05
    Pres
    -0.05
    .PostMapping
    -0.05
    ibr
    -0.05
    POSITIVE LOGITS
     determine
    0.08
    middle
    0.07
     concentrate
    0.07
    วย
    0.07
     "\">
    0.06
    Holder
    0.06
    UDP
    0.06
    ัญญ
    0.06
    ucceed
    0.06
    .allocate
    0.06
    Activations Density 0.012%

    No Known Activations