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. 11-RESID-POST-AA
    6. 20455
    Prev
    Next
    INDEX
    Explanations

    one

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    율
    -0.07
    (version
    -0.06
    nergy
    -0.06
    -testing
    -0.06
     vlan
    -0.06
    /domain
    -0.06
    stasy
    -0.06
     setImage
    -0.06
     SHR
    -0.06
     meis
    -0.06
    POSITIVE LOGITS
    odoxy
    0.07
     Brooke
    0.07
     Puppy
    0.07
    із
    0.06
     tropical
    0.06
    unders
    0.06
    $j
    0.06
    omit
    0.06
    (rc
    0.06
     Jahre
    0.06
    Activations Density 0.004%

    No Known Activations