© 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. 12666
    Prev
    Next
    INDEX
    Explanations

    DAMAGES

    np_max-act · gemini-2.0-flash

    The neuron triggers on occurrence of the all-caps term “DAMAGES” in boilerplate license/disclaimer text.

    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
    authorized
    -0.07
     대한
    -0.07
    、その
    -0.06
     secondo
    -0.06
     evidenced
    -0.06
     reluctance
    -0.06
    Seq
    -0.06
     MenuItem
    -0.06
    _cons
    -0.06
    _VERIFY
    -0.06
    POSITIVE LOGITS
     flea
    0.07
     gu
    0.07
     olmadığını
    0.06
     Cougar
    0.06
     Ace
    0.06
    ضافة
    0.06
     plaintext
    0.06
    venth
    0.06
    _secure
    0.06
    CBS
    0.06
    Activations Density 0.000%

    No Known Activations