© 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. 91506
    Prev
    Next
    INDEX
    Explanations

    Code/system messages

    np_max-act · gemini-2.0-flash

    The neuron is activated by the prompt’s section‐separator or heading tokens (e.g. “## Response:”) indicating the start of the assistant’s response section.

    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
     Tal
    -0.07
     VIII
    -0.07
     status
    -0.07
     opting
    -0.07
     Status
    -0.07
    ={$
    -0.06
     decided
    -0.06
    _dev
    -0.06
     Panic
    -0.06
     Policies
    -0.06
    POSITIVE LOGITS
    AnimationFrame
    0.07
    .surname
    0.06
    encoding
    0.06
    &w
    0.06
     unlawful
    0.06
     Ceramic
    0.06
     truyền
    0.06
     enerj
    0.06
     Deutsche
    0.06
     ejac
    0.06
    Activations Density 0.036%

    No Known Activations