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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 7-RESID-POST-AA
    6. 3927
    Prev
    Next
    INDEX
    Explanations

    init

    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
    discover
    -0.06
    IÓN
    -0.06
    EXPECTED
    -0.06
    中的
    -0.06
    TimeStamp
    -0.06
    opol
    -0.06
     overst
    -0.06
     Sandbox
    -0.06
    och
    -0.06
    统计
    -0.06
    POSITIVE LOGITS
     Interrupt
    0.07
    .author
    0.07
    Compiler
    0.07
     FB
    0.07
    .Receive
    0.07
    ApplicationBuilder
    0.06
     peter
    0.06
     Jimmy
    0.06
     j
    0.06
     James
    0.06
    Activations Density 0.000%

    No Known Activations