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. 10-LLAMASCOPE-RES-32K
    6. 11461
    Prev
    Next
    INDEX
    Explanations

    numerical data related to project costs and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aml
    -0.17
    anj
    -0.15
    æ³Ĭ
    -0.15
    лоп
    -0.14
     Traverse
    -0.14
    abyrin
    -0.14
    anel
    -0.13
    оба
    -0.13
    ATTRIBUTE
    -0.13
    coin
    -0.13
    POSITIVE LOGITS
    -old
    0.15
     Lyon
    0.14
     Overse
    0.14
    lyph
    0.14
    _snd
    0.14
    Watcher
    0.13
     Sandbox
    0.13
     Sang
    0.13
     rank
    0.13
    _kses
    0.13
    Activations Density 0.013%

    No Known Activations