© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74938
    Prev
    Next
    INDEX
    Explanations

    code/database references

    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_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
    -faced
    -0.06
     اینکه
    -0.06
    会
    -0.06
     premise
    -0.06
     incentives
    -0.06
    must
    -0.06
    yní
    -0.06
     antis
    -0.06
     consensus
    -0.06
     respons
    -0.06
    POSITIVE LOGITS
     Тур
    0.08
     значение
    0.08
     Ζ
    0.07
     conquer
    0.07
    英文
    0.07
    صن
    0.07
     gấp
    0.06
     작업
    0.06
    さらに
    0.06
    ίο
    0.06
    Activations Density 0.080%

    No Known Activations