Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84440
    Prev
    Next
    INDEX
    Explanations

    shame

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “shame” (especially in the phrase “it’s a shame”), i.e. expressions of regret or pity.

    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
    similar
    -0.07
    **
    -0.06
     metre
    -0.06
    .gf
    -0.06
     presidential
    -0.06
     да
    -0.06
    SOLE
    -0.06
    -target
    -0.06
     relaxed
    -0.06
    ecká
    -0.06
    POSITIVE LOGITS
     unfortunate
    0.10
     shame
    0.07
    چ
    0.06
     reluctant
    0.06
    損
    0.06
     pity
    0.06
    کس
    0.06
    ceased
    0.06
     Unfortunately
    0.06
     Newtown
    0.06
    Activations Density 0.014%

    No Known Activations