© 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. 20-LLAMASCOPE-RES-32K
    11. 29430
    Prev
    Next
    INDEX
    Explanations

    keywords related to project phases and various stages of product development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appendString
    -0.18
    hani
    -0.15
    elerik
    -0.15
    orz
    -0.15
    æľĢæĸ°
    -0.15
    æ³Ĭ
    -0.14
    ulpt
    -0.14
    conti
    -0.14
    lech
    -0.14
    à¹Ħà¸Łà¸Ł
    -0.14
    POSITIVE LOGITS
     initial
    0.34
     pre
    0.33
     Initial
    0.30
     preliminary
    0.30
     phase
    0.30
     Stage
    0.29
     Prel
    0.29
     Pre
    0.28
     Phase
    0.28
     prelim
    0.28
    Activations Density 0.269%

    No Known Activations