© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 2-LLAMASCOPE-RES-32K
    11. 9211
    Prev
    Next
    INDEX
    Explanations

    references to conclusions, theories, and philosophical queries related to existence and human understanding

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Advisor
    -0.16
     Agenda
    -0.14
    lash
    -0.14
     adm
    -0.14
    rompt
    -0.14
    pga
    -0.14
    abh
    -0.13
     falls
    -0.13
    dat
    -0.13
    aders
    -0.13
    POSITIVE LOGITS
    rvine
    0.15
    ureka
    0.14
    onta
    0.14
    ernote
    0.14
    avian
    0.14
    Occurred
    0.14
    Lifetime
    0.14
    158
    0.14
    URE
    0.13
    اÙĩا
    0.13
    Activations Density 1.327%

    No Known Activations