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. 7-RESID-POST-AA
    6. 86042
    Prev
    Next
    INDEX
    Explanations

    CEO

    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
    uliar
    -0.07
     laughed
    -0.07
    idd
    -0.07
    arded
    -0.06
    inte
    -0.06
     бед
    -0.06
    VENTORY
    -0.06
    (down
    -0.06
     Fish
    -0.06
     fairy
    -0.06
    POSITIVE LOGITS
     CEO
    0.17
    CEO
    0.14
     CEOs
    0.13
     CFO
    0.09
     CIM
    0.08
    -changing
    0.07
    MD
    0.07
    -ce
    0.07
     kg
    0.07
    cpu
    0.07
    Activations Density 0.006%

    No Known Activations