Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 122024
    Prev
    Next
    INDEX
    Explanations

    Vaughan

    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
    skou
    -0.06
     Becky
    -0.06
    stand
    -0.06
     refreshing
    -0.06
    Correct
    -0.06
     harbour
    -0.06
     hut
    -0.06
    بری
    -0.06
    Not
    -0.06
     بیماری
    -0.06
    POSITIVE LOGITS
     Vaughan
    0.25
     Vaugh
    0.24
     Watkins
    0.12
     Donovan
    0.09
     Paige
    0.08
    extras
    0.08
     웨
    0.07
     hoş
    0.07
    ――――
    0.06
    .throw
    0.06
    Activations Density 0.001%

    No Known Activations