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. 3-RESID-POST-AA
    6. 95051
    Prev
    Next
    INDEX
    Explanations

    Mr

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossil
    -0.07
    攻击
    -0.07
    orig
    -0.07
     UID
    -0.06
    (sub
    -0.06
     daher
    -0.06
    ẵ
    -0.06
     staples
    -0.06
     treatments
    -0.06
    iks
    -0.06
    POSITIVE LOGITS
     Mr
    0.10
    Mr
    0.08
     Mrs
    0.06
     Ms
    0.06
     Dr
    0.06
    .unbind
    0.06
    und
    0.06
     Ông
    0.06
     cookbook
    0.06
     شخصیت
    0.06
    Activations Density 0.010%

    No Known Activations