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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 92991
    Prev
    Next
    INDEX
    Explanations

    dial

    np_max-act · gemini-2.0-flash

    The neuron reliably activates on occurrences of the substring “bake” (e.g. in “bake,” “bakear,” etc.).

    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
     Studies
    -0.06
    玻璃
    -0.06
     ※
    -0.06
     Wholesale
    -0.06
     facebook
    -0.06
     periodo
    -0.06
     summoned
    -0.06
     Bunny
    -0.06
     Microsoft
    -0.06
     Martinez
    -0.06
    POSITIVE LOGITS
     quarantine
    0.06
    ERRUPT
    0.06
    сі
    0.06
    `;
    0.06
    -tip
    0.06
    .getElementById
    0.06
     dut
    0.06
    GEST
    0.06
    GRAPH
    0.06
    ś
    0.06
    Activations Density 0.300%

    No Known Activations