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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 998
    Prev
    Next
    INDEX
    Explanations

    shame

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “shame” or related shame-based words.

    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
     LiveData
    -0.07
    .buffer
    -0.07
    sat
    -0.06
    issant
    -0.06
     texto
    -0.06
     contemplated
    -0.06
    erosis
    -0.06
    serir
    -0.06
     Bird
    -0.06
    (path
    -0.06
    POSITIVE LOGITS
     shame
    0.13
     ashamed
    0.10
     Shame
    0.10
     shameful
    0.08
     stigma
    0.08
     disgrace
    0.08
    ime
    0.07
     in
    0.07
    ame
    0.06
    ين
    0.06
    Activations Density 0.004%

    No Known Activations