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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 27716
    Prev
    Next
    INDEX
    Explanations

    trim

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    몬
    -0.07
    олог
    -0.07
    (Constructor
    -0.07
    哥
    -0.06
    acas
    -0.06
     ocean
    -0.06
     Blob
    -0.06
    aga
    -0.06
     se
    -0.06
     Mundo
    -0.06
    POSITIVE LOGITS
     trimmed
    0.13
     trimming
    0.13
     trim
    0.11
     pruning
    0.10
    (trim
    0.09
     Trim
    0.08
    trimmed
    0.08
     урож
    0.08
    Trim
    0.08
     cut
    0.07
    Activations Density 0.005%

    No Known Activations