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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 3-RESID-POST-AA
    6. 122004
    Prev
    Next
    INDEX
    Explanations

    bottle

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    렇게
    -0.07
     hình
    -0.07
    /work
    -0.07
     разом
    -0.06
    면
    -0.06
    ιχ
    -0.06
    uries
    -0.06
     sınıf
    -0.06
    >',
    -0.06
     foes
    -0.06
    POSITIVE LOGITS
     bottle
    0.17
     Bott
    0.16
     Bottle
    0.15
     bottled
    0.09
     bott
    0.08
    ottle
    0.08
    OTT
    0.08
    �
    0.08
     bottleneck
    0.07
     belly
    0.07
    Activations Density 0.003%

    No Known Activations