© 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. 12552
    Prev
    Next
    INDEX
    Explanations

    Payments and financial support

    np_max-act · gemini-2.0-flash

    The neuron detects terms related to paid or sponsored content (e.g. payments, provisions, affiliate or commercial remuneration).

    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
    ukkan
    -0.07
    так
    -0.06
     '');↵↵
    -0.06
     uncover
    -0.06
    .createComponent
    -0.06
     "*"
    -0.06
          ↵↵
    -0.05
    <LM
    -0.05
    δος
    -0.05
     )
↵
↵
    -0.05
    POSITIVE LOGITS
    曾
    0.07
    Vol
    0.07
     positioning
    0.07
    _regression
    0.07
    ロー
    0.07
    intersect
    0.07
    织
    0.06
     muži
    0.06
     internet
    0.06
    대비
    0.06
    Activations Density 0.011%

    No Known Activations