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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 28418
    Prev
    Next
    INDEX
    Explanations

    references to specific racing events or competitions

    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
    oval
    -0.15
    onaut
    -0.15
    hide
    -0.15
    haus
    -0.15
    rl
    -0.15
     (*((
    -0.15
    ItemClick
    -0.15
    ences
    -0.14
    ertype
    -0.14
    hg
    -0.14
    POSITIVE LOGITS
    (IT
    0.21
    (AT
    0.18
    reshold
    0.17
    /TT
    0.17
    uber
    0.17
    aylor
    0.17
    esseract
    0.17
    ม
    0.16
    ting
    0.16
    ecta
    0.16
    Activations Density 0.103%

    No Known Activations