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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-LLAMASCOPE-RES-32K
    6. 9356
    Prev
    Next
    INDEX
    Explanations

    concepts related to algebraic topology and mathematical structures, particularly regarding cohomology rings and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    moth
    -0.17
    é«ĺæł¡
    -0.16
    ÏħÏĦÏĮ
    -0.15
     Harley
    -0.15
    igner
    -0.15
    Ïĥί
    -0.14
    ÑĢава
    -0.13
     Hungary
    -0.13
    ichel
    -0.13
     twins
    -0.13
    POSITIVE LOGITS
    iesel
    0.20
    _hierarchy
    0.16
    ieve
    0.15
     Spirits
    0.15
     Rings
    0.15
    TestFixture
    0.15
    ring
    0.15
    _operations
    0.14
    ansom
    0.14
     Vec
    0.14
    Activations Density 0.027%

    No Known Activations