© 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. 6944
    Prev
    Next
    INDEX
    Explanations

    adjectives describing feelings

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the word “positive” (and closely related upbeat, encouraging adjectives).

    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
     Zá
    -0.07
    kou
    -0.07
     Barry
    -0.06
     všichni
    -0.06
    Ban
    -0.06
     naï
    -0.06
    OVER
    -0.06
     suç
    -0.06
     Sunset
    -0.06
    очь
    -0.06
    POSITIVE LOGITS
     whim
    0.07
    цит
    0.07
    _qual
    0.06
     anomalies
    0.06
     bitterly
    0.06
    CommandEvent
    0.06
     بین
    0.06
     ورود
    0.06
    .getLatitude
    0.06
    ==============↵
    0.06
    Activations Density 0.055%

    No Known Activations