© 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. 109354
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the code imports or mentions the “bytes” package.

    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
     Slo
    -0.07
    iom
    -0.06
     Eff
    -0.06
     slee
    -0.06
    slick
    -0.06
    علوم
    -0.06
    ردد
    -0.06
     Glass
    -0.06
     Publisher
    -0.06
    _on
    -0.06
    POSITIVE LOGITS
    める
    0.07
     Prometheus
    0.06
     restrictive
    0.06
    )value
    0.06
    _NAME
    0.06
     attn
    0.06
     persuade
    0.06
     deltaTime
    0.06
    ンティ
    0.06
     "'",
    0.06
    Activations Density 0.000%

    No Known Activations