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. 19-RESID-POST-AA
    6. 83628
    Prev
    Next
    INDEX
    Explanations

    and,

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	ImGui
    -0.06
     Dev
    -0.06
    incre
    -0.06
    Ele
    -0.06
     prey
    -0.06
    Lv
    -0.06
     сель
    -0.06
    Produto
    -0.06
     lname
    -0.06
    邮
    -0.06
    POSITIVE LOGITS
    AGING
    0.08
    -blocking
    0.07
    oustic
    0.07
    ב
    0.07
     workers
    0.06
    یز
    0.06
     audition
    0.06
     handle
    0.06
     portable
    0.06
    -shell
    0.06
    Activations Density 0.056%

    No Known Activations