© 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. 7-RESID-POST-AA
    6. 4817
    Prev
    Next
    INDEX
    Explanations

    breach

    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
    /console
    -0.06
     pastry
    -0.06
     multiplier
    -0.06
     국제
    -0.06
    ски
    -0.06
     düzen
    -0.06
     impuls
    -0.06
    ющего
    -0.06
    visitor
    -0.06
    oll
    -0.06
    POSITIVE LOGITS
     breach
    0.14
     breaches
    0.10
     breached
    0.08
     BRE
    0.07
    .mContext
    0.07
    Branch
    0.07
     cheat
    0.07
    -tech
    0.07
    reach
    0.07
     cham
    0.07
    Activations Density 0.002%

    No Known Activations