© 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. 26-LLAMASCOPE-RES-32K
    11. 9935
    Prev
    Next
    INDEX
    Explanations

    instances of assurance and certainty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inand
    -0.15
    strup
    -0.14
    illez
    -0.14
    æľª
    -0.14
    ustum
    -0.14
    urette
    -0.14
    DTD
    -0.14
    BM
    -0.14
    δί
    -0.14
    ãĤĮãģ°
    -0.13
    POSITIVE LOGITS
     won
    0.77
    won
    0.69
     Won
    0.68
    Won
    0.64
     WON
    0.51
     wouldn
    0.45
     unlikely
    0.44
     wont
    0.43
    ä¸įä¼ļ
    0.39
     Wouldn
    0.35
    Activations Density 0.279%

    No Known Activations