© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 8970
    Prev
    Next
    INDEX
    Explanations

    in

    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
     Rig
    -0.07
    OL
    -0.07
     obj
    -0.07
     tir
    -0.07
     noise
    -0.06
     skill
    -0.06
     courts
    -0.06
     through
    -0.06
     What
    -0.06
    Building
    -0.06
    POSITIVE LOGITS
     اشاره
    0.07
     AssemblyCopyright
    0.06
    regs
    0.06
     gelişim
    0.06
     sorrow
    0.06
     นาง
    0.06
     ناح
    0.06
    fastcall
    0.06
     vědom
    0.06
    decltype
    0.06
    Activations Density 0.052%

    No Known Activations