© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43410
    Prev
    Next
    INDEX
    Explanations

    ac

    np_max-act · gemini-2.0-flash

    The neuron is attuned to long, multi‐syllabic word pieces—especially technical or hyphenated compound terms—marking their constituent token fragments with high activation.

    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
     gösterir
    -0.07
    ▲
    -0.07
     requestCode
    -0.07
     viz
    -0.06
    γου
    -0.06
    ább
    -0.06
    運動
    -0.06
     yiy
    -0.06
    _PUSH
    -0.06
     Tours
    -0.06
    POSITIVE LOGITS
    -of
    0.07
    ведите
    0.06
    428
    0.06
     что
    0.06
    ğer
    0.06
    Scanner
    0.06
     кры
    0.06
    "name
    0.06
    "indices
    0.06
    417
    0.06
    Activations Density 0.007%

    No Known Activations