© 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. 3-RESID-POST-AA
    11. 122987
    Prev
    Next
    INDEX
    Explanations

    bamboo

    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
    487
    -0.07
     validate
    -0.07
     McA
    -0.07
    Initializer
    -0.06
    -Core
    -0.06
     Jian
    -0.06
     majestic
    -0.06
     ổn
    -0.06
     об
    -0.06
    ured
    -0.06
    POSITIVE LOGITS
     BMW
    0.16
     bamboo
    0.16
     Memphis
    0.15
    BMW
    0.15
     Bamboo
    0.13
     Fargo
    0.11
     cargo
    0.10
     entrusted
    0.10
     Georgetown
    0.10
     Ferdinand
    0.09
    Activations Density 0.007%

    No Known Activations