© 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. 55796
    Prev
    Next
    INDEX
    Explanations

    spirit

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the word “spirit.”

    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
     cole
    -0.07
     McCabe
    -0.07
     Hale
    -0.06
     Morton
    -0.06
     College
    -0.06
     Ober
    -0.06
     baz
    -0.06
    Alloc
    -0.06
    anooga
    -0.06
     mcc
    -0.06
    POSITIVE LOGITS
     spirit
    0.17
     Spirit
    0.16
     spirits
    0.14
    spirit
    0.12
    Spirit
    0.12
     Spirits
    0.12
     spiritual
    0.11
    pirit
    0.09
     روح
    0.09
    spi
    0.09
    Activations Density 0.009%

    No Known Activations