© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 8954
    Prev
    Next
    INDEX
    Explanations

    islands

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORE
    -0.06
     Libraries
    -0.06
     engage
    -0.06
    angep
    -0.06
     rien
    -0.06
     Luxury
    -0.06
    ==>
    -0.06
    Curr
    -0.06
    .fil
    -0.06
    Lastly
    -0.06
    POSITIVE LOGITS
     upset
    0.07
    ひと
    0.07
     whore
    0.07
     шту
    0.06
     pcs
    0.06
     trhu
    0.06
     atIndex
    0.06
    巻
    0.06
    eks
    0.06
     madness
    0.06
    Activations Density 0.000%

    No Known Activations