© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 9026
    Prev
    Next
    INDEX
    Explanations

    conclude

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of “conclude” (and its morphological variants like “conclusion,” “concluded,” “conclude,” 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
     sexdate
    -0.07
    376
    -0.07
    .MediaType
    -0.07
    /font
    -0.07
    ARCHAR
    -0.07
     life
    -0.07
    life
    -0.07
     Terraria
    -0.06
     sport
    -0.06
    YTE
    -0.06
    POSITIVE LOGITS
     concluded
    0.13
     conclusion
    0.12
     conclude
    0.12
     conclusions
    0.12
     concluding
    0.12
     conclus
    0.10
     concludes
    0.10
    结
    0.09
     concl
    0.09
    Dec
    0.08
    Activations Density 0.014%

    No Known Activations