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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 94190
    Prev
    Next
    INDEX
    Explanations

    other

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deadly
    -0.06
     NOTHING
    -0.06
     imageNamed
    -0.06
     cheating
    -0.06
     renovated
    -0.06
     getTime
    -0.06
     Antwort
    -0.06
    _buffer
    -0.05
     resist
    -0.05
     scandals
    -0.05
    POSITIVE LOGITS
    古屋
    0.07
    TEL
    0.07
     Last
    0.07
    电视
    0.06
    -navbar
    0.06
    typings
    0.06
     third
    0.06
     hollow
    0.06
     Olympus
    0.06
    Unix
    0.06
    Activations Density 0.005%

    No Known Activations