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. 15-RESID-POST-AA
    6. 121608
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    区域
    -0.06
    -download
    -0.06
    락
    -0.06
    	report
    -0.06
     çıkış
    -0.06
    йте
    -0.06
     SOCIAL
    -0.05
    рім
    -0.05
     ben
    -0.05
     criterion
    -0.05
    POSITIVE LOGITS
    .—
    0.07
     uvád
    0.07
     sar
    0.07
    طع
    0.07
     chol
    0.06
     Caj
    0.06
    loom
    0.06
    ()%
    0.06
    []):
    0.06
    elige
    0.06
    Activations Density 0.000%

    No Known Activations