© 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. 18-LLAMASCOPE-RES-32K
    11. 15511
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to chat systems and artificial intelligence methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kili
    -0.15
     pelic
    -0.15
    меÑĤÑĮ
    -0.14
     Imported
    -0.14
     conquer
    -0.14
     RADIO
    -0.14
    phin
    -0.14
     passive
    -0.14
     gro
    -0.13
     Passive
    -0.13
    POSITIVE LOGITS
    GAN
    0.21
     Maher
    0.16
     Gener
    0.16
     output
    0.15
     Generator
    0.15
     gener
    0.15
    .generator
    0.14
    goo
    0.14
    gan
    0.14
    -generator
    0.14
    Activations Density 0.005%

    No Known Activations