© 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. 91541
    Prev
    Next
    INDEX
    Explanations

    Code documentation

    np_max-act · gemini-2.0-flash

    The neuron activates on structural markup tokens—i.e. the bracketed labels and tag delimiters (like “[”, “/”, and tag names) that mark sections of the text.

    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
     "=",
    -0.06
     CONSTANT
    -0.06
    ーテ
    -0.06
     Fans
    -0.06
     운
    -0.06
    �인
    -0.06
    ือถ
    -0.06
     Tire
    -0.06
     assum
    -0.06
     通
    -0.05
    POSITIVE LOGITS
     Ashley
    0.07
     PS
    0.07
     Programmer
    0.06
     Banana
    0.06
    PixelFormat
    0.06
     murderer
    0.06
    enz
    0.06
    education
    0.06
     prisoner
    0.06
    -highlight
    0.06
    Activations Density 0.007%

    No Known Activations