© 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. 13150
    Prev
    Next
    INDEX
    Explanations

    Conditional questions

    np_max-act · gemini-2.0-flash

    The neuron activates on reporter‐question phrasing—especially occurrences of “asked” or “when asked if/whether,” marking interview or question contexts.

    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
    .borderColor
    -0.07
    aklı
    -0.07
    exas
    -0.06
    افت
    -0.06
    atik
    -0.06
     Chloe
    -0.06
     goodies
    -0.06
    ki
    -0.06
    ocolate
    -0.06
     PROCUREMENT
    -0.06
    POSITIVE LOGITS
    _multiple
    0.07
    _();↵
    0.07
     ')'
    0.07
     mí
    0.06
     geliştir
    0.06
    .='
    0.06
    ]);
    0.06
    _REV
    0.06
     Пок
    0.06
    resultado
    0.06
    Activations Density 0.018%

    No Known Activations