© 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. 126779
    Prev
    Next
    INDEX
    Explanations

    cheering, support

    np_max-act · gemini-2.0-flash

    This neuron detects phrases expressing personal support or cheering (e.g., “root for my favorite players,” “cheering on …”).

    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
     trailer
    -0.07
    ))))
    -0.07
     find
    -0.06
     mnoha
    -0.06
    睡
    -0.06
    /Error
    -0.06
     kde
    -0.06
     hroz
    -0.06
     "/"
    -0.06
    ))),
    -0.06
    POSITIVE LOGITS
    stood
    0.07
     إذ
    0.07
     onward
    0.07
     extinct
    0.07
    Separated
    0.06
    puty
    0.06
    .out
    0.06
     consolidated
    0.06
    dete
    0.06
    کت
    0.06
    Activations Density 0.004%

    No Known Activations