© 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. 11-RESID-POST-AA
    11. 58772
    Prev
    Next
    INDEX
    Explanations

    Error/Exception handling (code)

    np_max-act · gemini-2.0-flash

    The neuron flags exception‐handling constructs (e.g. try/catch blocks and “expected” error annotations).

    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
     irrit
    -0.07
    732
    -0.07
    Ram
    -0.07
    Hard
    -0.06
     chilly
    -0.06
    Didn
    -0.06
     рей
    -0.06
    Detach
    -0.06
    Naz
    -0.06
    Collapsed
    -0.06
    POSITIVE LOGITS
    'L
    0.07
    ты
    0.06
     �
    0.06
     plur
    0.06
     already
    0.06
    ورد
    0.06
    iting
    0.06
     ↵
    0.06
     fruition
    0.06
    .gridx
    0.06
    Activations Density 0.009%

    No Known Activations