© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 13246
    Prev
    Next
    INDEX
    Explanations

    terminology related to contracts and regulations in healthcare and government sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocl
    -0.19
    /cli
    -0.17
    ompiler
    -0.16
    .Collection
    -0.16
     clk
    -0.15
    ÑĢиз
    -0.15
     Again
    -0.15
     CLK
    -0.15
     Chick
    -0.15
    nemonic
    -0.15
    POSITIVE LOGITS
     rather
    0.34
     instead
    0.32
    rather
    0.28
    instead
    0.26
     Rather
    0.26
     Instead
    0.23
    Rather
    0.23
    Instead
    0.23
     вмеÑģÑĤ
    0.21
    DAQ
    0.18
    Activations Density 0.041%

    No Known Activations