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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 27-RESID-POST-AA
    6. 108914
    Prev
    Next
    INDEX
    Explanations

    website

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saç
    -0.07
    variants
    -0.06
    ernel
    -0.06
    oltage
    -0.06
    uman
    -0.06
     shall
    -0.06
     wię
    -0.06
    aking
    -0.06
    _groups
    -0.06
    North
    -0.06
    POSITIVE LOGITS
     Dod
    0.07
    298
    0.06
     dop
    0.06
    eği
    0.06
     temple
    0.06
    ังก
    0.06
     einer
    0.06
    #"
    0.06
     plane
    0.06
    etiyle
    0.06
    Activations Density 0.004%

    No Known Activations