© 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. 27-RESID-POST-AA
    11. 103885
    Prev
    Next
    INDEX
    Explanations

    mixed languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PubMed
    -0.07
    預
    -0.07
     suit
    -0.07
    vas
    -0.07
    -lines
    -0.07
    лює
    -0.06
     market
    -0.06
     Furn
    -0.06
     adulthood
    -0.06
    	FROM
    -0.06
    POSITIVE LOGITS
    ixedReality
    0.06
     Чер
    0.06
    ¨¨
    0.06
    AGMA
    0.06
    .AsyncTask
    0.06
     USART
    0.06
     reorder
    0.06
    )$/
    0.05
     Ara
    0.05
    pop
    0.05
    Activations Density 0.060%

    No Known Activations