© 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. 109659
    Prev
    Next
    INDEX
    Explanations

    neural network layer sizes

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literal tokens (especially floating-point numbers) in code.

    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
     podporu
    -0.07
    .errors
    -0.07
    .Container
    -0.07
    Incre
    -0.07
    "indices
    -0.06
    _strlen
    -0.06
     "...
    -0.06
    .SetBool
    -0.06
     resizeMode
    -0.06
    .Search
    -0.06
    POSITIVE LOGITS
     cigaret
    0.07
     Counties
    0.07
    vx
    0.07
     sire
    0.06
     Verde
    0.06
     UIAlert
    0.06
     lia
    0.06
     considerable
    0.06
     hakkı
    0.06
    団
    0.06
    Activations Density 0.011%

    No Known Activations