© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 1843
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until" indicating temporal conditions or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¾ãģ¾
    -0.16
    ãĥ¼ãĥĬ
    -0.15
    ony
    -0.14
    ãģ¹ãģį
    -0.14
    رÙĤ
    -0.14
    ours
    -0.14
    xeb
    -0.13
     ÑĥÑĩаÑģÑĤи
    -0.13
    áo
    -0.13
    à¹Ħว
    -0.13
    POSITIVE LOGITS
    /un
    0.32
     they
    0.30
     recently
    0.26
     it
    0.25
     such
    0.24
     we
    0.24
    /if
    0.23
     someone
    0.23
     further
    0.21
     reaching
    0.21
    Activations Density 0.049%

    No Known Activations