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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RESID-POST-AA
    11. 121297
    Prev
    Next
    INDEX
    Explanations

    mammals

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...,
    -0.07
     brig
    -0.06
     erro
    -0.06
    264
    -0.06
     comando
    -0.06
    يلم
    -0.06
    Univers
    -0.06
    ron
    -0.06
    -be
    -0.06
    sınız
    -0.06
    POSITIVE LOGITS
     mammals
    0.32
     mamm
    0.09
     Sabb
    0.07
     Passed
    0.07
     Pointer
    0.06
    „J
    0.06
     userManager
    0.06
    ظٹط
    0.06
     Shel
    0.06
    =C
    0.06
    Activations Density 0.002%

    No Known Activations