© 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. 25-LLAMASCOPE-RES-32K
    11. 14910
    Prev
    Next
    INDEX
    Explanations

    references to cost estimates and quotes for services

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    indsight
    -0.15
     cerc
    -0.14
    ÚĨÛĮ
    -0.14
    onet
    -0.14
    гаÑĢ
    -0.14
    æĻĤ代
    -0.14
    ÙĪÙĨد
    -0.13
    oyer
    -0.13
     Ezra
    -0.13
    /gtest
    -0.13
    POSITIVE LOGITS
     quote
    0.77
     quotes
    0.72
     quotation
    0.67
     Quote
    0.66
     quotations
    0.64
    -quote
    0.63
     Quotes
    0.62
    quote
    0.59
    Quote
    0.58
    quotes
    0.57
    Activations Density 0.199%

    No Known Activations