© 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 (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 45471
    Prev
    Next
    INDEX
    Explanations

    Australian locations

    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
    .recv
    -0.07
    すれば
    -0.06
    投注
    -0.06
     هنگ
    -0.06
                                                                                           
    -0.06
    '));
    ↵
    -0.06
     topology
    -0.06
     propagation
    -0.06
     TestCase
    -0.06
     الأح
    -0.06
    POSITIVE LOGITS
     zim
    0.10
    IMP
    0.09
    imb
    0.09
    imid
    0.09
    imer
    0.09
    IM
    0.08
    imus
    0.08
    ima
    0.08
    im
    0.08
    imers
    0.08
    Activations Density 0.021%

    No Known Activations