© 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. 73739
    Prev
    Next
    INDEX
    Explanations

    stabil

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens related to “stabilize” (e.g. stability, stabilizes, stabilizing), i.e. mentions of molecular or protein/RNA stability.

    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
     Sport
    -0.06
    Lou
    -0.06
    Blank
    -0.06
    okino
    -0.06
     scape
    -0.06
     Avengers
    -0.06
     wipes
    -0.06
    them
    -0.06
    Binary
    -0.06
    Bar
    -0.06
    POSITIVE LOGITS
    .Real
    0.07
     Kickstarter
    0.07
     stabilized
    0.07
    _THROW
    0.07
     이후
    0.07
    ="<?=$
    0.07
     TSRMLS
    0.06
     شناسی
    0.06
     утвержд
    0.06
     mensen
    0.06
    Activations Density 0.007%

    No Known Activations