© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 21549
    Prev
    Next
    INDEX
    Explanations

    brief

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Val
    -0.07
     freshwater
    -0.07
     зрост
    -0.06
    XYZ
    -0.06
     visualize
    -0.06
    tooltip
    -0.06
     lol
    -0.06
     Hunts
    -0.06
     نگهداری
    -0.06
     hợp
    -0.06
    POSITIVE LOGITS
     sid
    0.06
    .multi
    0.06
     zm
    0.06
     gorge
    0.06
    182
    0.06
     سه
    0.06
     mx
    0.06
    (case
    0.06
    517
    0.06
    Ю
    0.06
    Activations Density 0.002%

    No Known Activations