© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7793
    Prev
    Next
    INDEX
    Explanations

    ikes

    np_max-act · gemini-2.0-flash

    This neuron consistently lights up on the little decimal‐fraction annotations (e.g. “0.6044921875,” “0.4140625,” etc.) that appear in the metadata rather than on the actual text tokens.

    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
     と
    -0.06
    _quit
    -0.06
     astronauts
    -0.06
    adu
    -0.06
     bullying
    -0.06
     Лю
    -0.06
    řaz
    -0.06
     buyer
    -0.06
    (instruction
    -0.06
    deg
    -0.06
    POSITIVE LOGITS
    賽
    0.06
     nd
    0.06
     Sebast
    0.06
     obe
    0.06
     STREAM
    0.06
     أغ
    0.06
     Ches
    0.06
     james
    0.05
    UILayout
    0.05
    .cwd
    0.05
    Activations Density 0.133%

    No Known Activations