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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41693
    Prev
    Next
    INDEX
    Explanations

    Copyright

    np_max-act · gemini-2.0-flash

    The neuron activates on copyright/license header lines, i.e. it detects “Copyright” notices at the top of source files.

    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
    (l
    -0.07
     Shoe
    -0.06
    266
    -0.06
    (m
    -0.06
    _TS
    -0.06
    .getJSONObject
    -0.06
    asel
    -0.06
    hints
    -0.06
    _CUDA
    -0.06
    —they
    -0.06
    POSITIVE LOGITS
    Trait
    0.07
     Wayne
    0.06
     breakpoints
    0.06
    Money
    0.06
    ा↵↵
    0.06
     basis
    0.06
    ANDING
    0.06
     Reds
    0.06
     designer
    0.06
    seconds
    0.06
    Activations Density 0.001%

    No Known Activations