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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21374
    Prev
    Next
    INDEX
    Explanations

    on

    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
    SetText
    -0.07
    cai
    -0.06
     rovněž
    -0.06
    ru
    -0.06
    	send
    -0.06
    攻击
    -0.06
     佐
    -0.06
    údo
    -0.06
    กระ
    -0.06
    پس
    -0.06
    POSITIVE LOGITS
    /full
    0.07
    39
    0.07
    .limit
    0.07
     sulfur
    0.06
     unlink
    0.06
    ΙΚ
    0.06
     RM
    0.06
     الرح
    0.06
    .qt
    0.06
     ب
    0.06
    Activations Density 0.000%

    No Known Activations