© 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. 41466
    Prev
    Next
    INDEX
    Explanations

    ist

    np_max-act · gemini-2.0-flash

    This neuron fires whenever the text mentions the MNIST dataset (its name or related terms).

    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
    ění
    -0.07
     RTAL
    -0.07
     energ
    -0.07
    \Type
    -0.07
     AssemblyCompany
    -0.06
    ienne
    -0.06
     Hava
    -0.06
    jde
    -0.06
    .ne
    -0.06
    entialAction
    -0.06
    POSITIVE LOGITS
     appears
    0.07
     wears
    0.07
     arising
    0.07
     wear
    0.07
     appear
    0.06
     clean
    0.06
     Naruto
    0.06
     NI
    0.06
    escaped
    0.06
     electron
    0.06
    Activations Density 0.006%

    No Known Activations