© 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. 123696
    Prev
    Next
    INDEX
    Explanations

    Ti

    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
     الد
    -0.07
     transl
    -0.07
     elimin
    -0.07
    	JSONObject
    -0.06
     elong
    -0.06
    oleans
    -0.06
     ammon
    -0.06
    私は
    -0.06
    _questions
    -0.06
     shady
    -0.06
    POSITIVE LOGITS
    Ti
    0.18
     Ti
    0.17
     titanium
    0.07
    wi
    0.06
     tv
    0.06
    msgs
    0.06
    τη
    0.06
    Pix
    0.06
    Follow
    0.06
    �
    0.06
    Activations Density 0.003%

    No Known Activations