© 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. 6592
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron activates on top‐level declaration keywords in code (e.g. “protocol,” “model,” “data,” “proc,” “package,” etc.).

    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
     discoveries
    -0.07
     Eden
    -0.07
    IES
    -0.06
    .mime
    -0.06
    foon
    -0.06
     Vere
    -0.06
     Zag
    -0.06
     PropertyValue
    -0.06
     Bapt
    -0.06
    PARSE
    -0.06
    POSITIVE LOGITS
    ()]
    0.06
    ̆
    0.06
    ublic
    0.06
     pornografia
    0.06
     ('$
    0.06
    �
    0.06
     рабоч
    0.06
     Specifically
    0.06
    сим
    0.06
    odata
    0.06
    Activations Density 0.047%

    No Known Activations