© 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. 31-LLAMASCOPE-RES-32K
    11. 22258
    Prev
    Next
    INDEX
    Explanations

    numerical data related to financial and contractual metrics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    tring
    -0.14
    izmet
    -0.14
    unsqueeze
    -0.13
    .rpm
    -0.13
    bersome
    -0.13
    ÙĴد
    -0.13
     weren
    -0.13
     erken
    -0.13
    ë°ĺ
    -0.13
    _literals
    -0.12
    POSITIVE LOGITS
     amounted
    0.34
     ranges
    0.33
     amounts
    0.33
     stands
    0.32
     stood
    0.31
     totaled
    0.29
     equals
    0.29
     ranged
    0.29
     ÑģоÑģÑĤавлÑıеÑĤ
    0.28
     equ
    0.28
    Activations Density 0.149%

    No Known Activations