© 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. 63134
    Prev
    Next
    INDEX
    Explanations

    probability questions

    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
    aggio
    -0.07
     Điều
    -0.06
    ->___
    -0.06
     bustling
    -0.06
     Sexo
    -0.06
     Seg
    -0.06
     franc
    -0.06
     infring
    -0.06
    ，就
    -0.06
    е�
    -0.06
    POSITIVE LOGITS
    (space
    0.07
     alterations
    0.06
     dent
    0.06
     adı
    0.06
     PROM
    0.06
    .vertex
    0.06
    จะได
    0.06
     FB
    0.06
    eter
    0.06
     Fior
    0.06
    Activations Density 0.002%

    No Known Activations