© 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. 7-RESID-POST-AA
    11. 119934
    Prev
    Next
    INDEX
    Explanations

    es

    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
     achievements
    -0.07
    terminal
    -0.06
     oprav
    -0.06
     때
    -0.06
    люч
    -0.06
     practical
    -0.06
    pression
    -0.06
     écrit
    -0.06
    _cls
    -0.06
    .Fatalf
    -0.06
    POSITIVE LOGITS
     rates
    0.07
    ountains
    0.07
    Schedulers
    0.07
     quantities
    0.07
    URES
    0.07
     levels
    0.07
    ocities
    0.06
    setDefault
    0.06
     DropIndex
    0.06
     temperatures
    0.06
    Activations Density 0.183%

    No Known Activations