© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6940
    Prev
    Next
    INDEX
    Explanations

    breath

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “shortness of breath” (or closely similar phrasing indicating breathing difficulty).

    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
    .YES
    -0.07
    уванням
    -0.06
    _format
    -0.06
    StandardItem
    -0.06
     controlId
    -0.06
    GLOSS
    -0.06
     Tommy
    -0.06
     Unters
    -0.06
     yacc
    -0.06
    printf
    -0.06
    POSITIVE LOGITS
     inst
    0.07
    Dream
    0.07
    .multi
    0.06
     immedi
    0.06
     ↵↵
    0.06
     tog
    0.06
     sedm
    0.06
     vers
    0.06
    Produces
    0.06
      	↵
    0.06
    Activations Density 0.004%

    No Known Activations