Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 13912
    Prev
    Next
    INDEX
    Explanations

    significant dates and milestones in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ting
    -0.18
    ly
    -0.16
    ning
    -0.16
     ing
    -0.15
    tx
    -0.15
    elsing
    -0.15
     lact
    -0.15
     Trad
    -0.15
    de
    -0.14
    ALAR
    -0.14
    POSITIVE LOGITS
    ucht
    0.16
    onya
    0.15
    ahas
    0.15
     -*-č↵
    0.15
    oram
    0.15
    harma
    0.15
    TEGER
    0.14
    Bid
    0.14
    sville
    0.14
    ÄĽtÃŃ
    0.14
    Activations Density 0.015%

    No Known Activations