© 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. 28-LLAMASCOPE-RES-32K
    11. 17645
    Prev
    Next
    INDEX
    Explanations

    references to email-related settings and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulos
    -0.18
    zos
    -0.15
    edl
    -0.14
    çak
    -0.14
     NONINFRINGEMENT
    -0.14
    ssel
    -0.14
    isko
    -0.14
    USB
    -0.14
    uibModal
    -0.14
     Wenger
    -0.13
    POSITIVE LOGITS
     POP
    0.33
     imap
    0.31
     mail
    0.31
     IM
    0.30
     mailbox
    0.30
     Exchange
    0.28
     Mail
    0.28
     Outlook
    0.28
    Exchange
    0.28
    POP
    0.28
    Activations Density 0.068%

    No Known Activations