© 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. 21-LLAMASCOPE-RES-32K
    11. 20417
    Prev
    Next
    INDEX
    Explanations

    statistical expressions and comparative analysis in scientific data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {};č↵
    -0.14
    +xml
    -0.14
    doctype
    -0.14
    chen
    -0.14
     (£
    -0.14
    hecy
    -0.14
    зÑĥ
    -0.13
     Paladin
    -0.13
    Mapped
    -0.13
     Rowe
    -0.13
    POSITIVE LOGITS
     =
    0.38
    =
    0.35
     =↵
    0.21
     ==
    0.19
     value
    0.19
     values
    0.17
    =$
    0.17
     Pending
    0.17
    odem
    0.17
    =`
    0.17
    Activations Density 0.054%

    No Known Activations