Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 5185
    Prev
    Next
    INDEX
    Explanations

    spirit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     College
    -0.08
     maxX
    -0.06
     marble
    -0.06
     Checklist
    -0.06
    _answer
    -0.06
    993
    -0.06
     accessed
    -0.06
     Rosen
    -0.06
     θέση
    -0.06
     vacc
    -0.06
    POSITIVE LOGITS
     spirit
    0.19
     Spirit
    0.18
     spirits
    0.16
    Spirit
    0.15
     Spirits
    0.13
    spirit
    0.12
    pirit
    0.09
     SPI
    0.09
     spiritual
    0.09
     spirited
    0.09
    Activations Density 0.009%

    No Known Activations