© 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. 8897
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron fires on call-to-action and promotional language—phrases inviting the reader to download, visit, register, get in touch, or take similar marketing steps.

    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
     nets
    -0.07
     tourism
    -0.06
     traps
    -0.06
    quest
    -0.06
    Ki
    -0.06
     tapes
    -0.06
    pga
    -0.06
     Chase
    -0.06
     model
    -0.06
    Recording
    -0.06
    POSITIVE LOGITS
     mutlak
    0.07
     {}.
    0.07
    .Reset
    0.07
    ).'
    0.07
     trif
    0.07
     เมษายน
    0.06
     yaptık
    0.06
    .Sqrt
    0.06
     SOUR
    0.06
     quelque
    0.06
    Activations Density 0.059%

    No Known Activations