© 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. 125167
    Prev
    Next
    INDEX
    Explanations

    Bad things happening

    np_max-act · gemini-2.0-flash

    references to safety and security concerns, particularly in relation to violent incidents or attacks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on tokens in step‐by‐step advice or instructional/explanatory passages.

    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
     Auburn
    -0.07
    previous
    -0.07
     procurement
    -0.06
     venez
    -0.06
     hadn
    -0.06
    ”,
    -0.06
    散
    -0.06
    _mode
    -0.06
     scam
    -0.06
     turtles
    -0.06
    POSITIVE LOGITS
     AutoMapper
    0.07
    ícia
    0.07
    یزات
    0.07
     gren
    0.06
    ()>
    0.06
     strany
    0.06
     nového
    0.06
    /GL
    0.06
     RAT
    0.06
    dr
    0.06
    Activations Density 0.063%

    No Known Activations