© 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. 34897
    Prev
    Next
    INDEX
    Explanations

    dro

    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
     Mean
    -0.07
    ájem
    -0.07
     Cz
    -0.07
    etail
    -0.07
    >Please
    -0.07
     meaningless
    -0.06
    antan
    -0.06
     koşul
    -0.06
     McKay
    -0.06
    cence
    -0.06
    POSITIVE LOGITS
     Hydro
    0.08
     hydro
    0.08
     doprav
    0.08
     hydraulic
    0.06
     dehydration
    0.06
    thinkable
    0.06
    持续
    0.06
     сух
    0.06
    018
    0.06
     nombreux
    0.06
    Activations Density 0.012%

    No Known Activations