© 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. 7345
    Prev
    Next
    INDEX
    Explanations

    throttle

    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
     spolupráci
    -0.07
     asserting
    -0.06
     pearls
    -0.06
     жит
    -0.06
    さんが
    -0.06
    camp
    -0.06
     cemetery
    -0.06
     age
    -0.06
     недели
    -0.06
    Ocean
    -0.06
    POSITIVE LOGITS
     throttle
    0.18
    rottle
    0.11
     thrott
    0.11
    trl
    0.07
     provoz
    0.07
    rtl
    0.07
     Thr
    0.07
    �
    0.07
    .flash
    0.07
    le
    0.07
    Activations Density 0.001%

    No Known Activations