© 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. 35530
    Prev
    Next
    INDEX
    Explanations

    Answers

    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
    Nr
    -0.07
     briefly
    -0.06
     beat
    -0.06
     aantal
    -0.06
     HEAD
    -0.06
    uD
    -0.06
     bunch
    -0.06
    Dep
    -0.06
    AK
    -0.06
     HPV
    -0.06
    POSITIVE LOGITS
    ://%
    0.07
    ζα
    0.07
     vysvět
    0.07
     مستق
    0.07
    eceği
    0.07
    ่ร
    0.06
    utral
    0.06
    Signing
    0.06
    ặn
    0.06
    quartered
    0.06
    Activations Density 0.000%

    No Known Activations