© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30522
    Prev
    Next
    INDEX
    Explanations

    self improvement

    np_max-act · gemini-2.0-flash

    suggestions for personal improvement and self-development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on language about giving or seeking self‐improvement and life‐advice—“how to” tips for personal growth, improving one’s life, habits, or well‐being.

    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
    gatsby
    -0.06
     βασ
    -0.06
    .observable
    -0.06
     ############
    -0.06
    uki
    -0.06
     Prot
    -0.06
     报
    -0.06
     للد
    -0.06
    ，该
    -0.06
     overlaps
    -0.06
    POSITIVE LOGITS
     домаш
    0.07
     admit
    0.07
    ุน
    0.06
    ैं।
    0.06
    Hostname
    0.06
     marital
    0.06
    쪽
    0.06
    buyer
    0.06
     bets
    0.06
     battalion
    0.06
    Activations Density 0.173%

    No Known Activations