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. 73119
    Prev
    Next
    INDEX
    Explanations

    article

    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
     burner
    -0.07
     detta
    -0.07
    backend
    -0.06
     rv
    -0.06
     Suites
    -0.06
     Approval
    -0.06
     announces
    -0.06
     intf
    -0.06
     Bridges
    -0.06
    Address
    -0.06
    POSITIVE LOGITS
    ensely
    0.08
    ...</
    0.07
    ozy
    0.07
    green
    0.06
    Que
    0.06
    Qué
    0.06
    uje
    0.06
     apologise
    0.06
    !</
    0.06
     Familie
    0.06
    Activations Density 0.018%

    No Known Activations