© 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 EvalsExportsinterp-engineNEWAPI 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. 115800
    Prev
    Next
    INDEX
    Explanations

    3

    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
     رفته
    -0.07
    ord
    -0.07
     Podle
    -0.07
    _EFFECT
    -0.07
    elm
    -0.07
     patří
    -0.07
    Na
    -0.06
     obvyk
    -0.06
    řiv
    -0.06
     Gn
    -0.06
    POSITIVE LOGITS
    incipal
    0.07
    	logging
    0.06
    willReturn
    0.06
    .house
    0.06
     intrigue
    0.06
    套
    0.06
    thinkable
    0.06
    hom
    0.06
     Compliance
    0.06
    صت
    0.06
    Activations Density 0.017%

    No Known Activations