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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RESID-POST-AA
    11. 95404
    Prev
    Next
    INDEX
    Explanations

    Kart

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edef
    -0.06
    ánh
    -0.06
    cribes
    -0.06
    antiago
    -0.06
     simplistic
    -0.06
     Static
    -0.06
    นค
    -0.06
    ete
    -0.06
    ۱۳۸
    -0.06
    	self
    -0.06
    POSITIVE LOGITS
    Intro
    0.07
     FILTER
    0.06
    _BR
    0.06
     conducted
    0.06
     จำนวน
    0.06
    Extract
    0.06
     حساب
    0.06
    .“
    0.06
    από
    0.06
    Forest
    0.06
    Activations Density 0.011%

    No Known Activations