Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 80598
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     components
    -0.07
     unreliable
    -0.07
    Adjust
    -0.06
    вичай
    -0.06
    سته
    -0.06
    عي
    -0.06
    оро
    -0.06
     invalidated
    -0.06
    ●●●●●●●●
    -0.06
    μένες
    -0.06
    POSITIVE LOGITS
    Hang
    0.06
    HostName
    0.06
     faz
    0.06
     eig
    0.06
     آپ
    0.06
    .Spring
    0.06
    (Path
    0.06
     testim
    0.06
     irgend
    0.06
    [pos
    0.06
    Activations Density 0.046%

    No Known Activations