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

    Neuronpedia

    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. 28-LLAMASCOPE-RES-32K
    11. 30459
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements related to duration, distance, and weight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eki
    -0.16
    ÑĴ
    -0.15
    olet
    -0.15
    vala
    -0.14
    erah
    -0.14
    jen
    -0.14
     Millions
    -0.13
    ÅŁk
    -0.13
    quential
    -0.13
    ÑĽ
    -0.13
    POSITIVE LOGITS
     maximum
    0.35
     minimum
    0.35
     max
    0.33
     depending
    0.30
     tops
    0.29
    minimum
    0.28
    maximum
    0.28
     MAX
    0.27
    å·¦åı³
    0.26
     макÑģим
    0.25
    Activations Density 0.219%

    No Known Activations