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. 16-LLAMASCOPE-RES-32K
    6. 1713
    Prev
    Next
    INDEX
    Explanations

    key terms related to educational contexts and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eker
    -0.21
     Gem
    -0.17
    uni
    -0.15
     Vand
    -0.15
    aken
    -0.15
     stat
    -0.14
    opper
    -0.14
     bs
    -0.14
    AKER
    -0.14
    bs
    -0.14
    POSITIVE LOGITS
    Unhandled
    0.16
    Owned
    0.16
    enty
    0.15
     Owned
    0.14
    FRING
    0.14
    orre
    0.14
    ÙĪØ¬ÙĪØ¯
    0.14
    ippets
    0.14
    ContentAlignment
    0.14
    yntax
    0.14
    Activations Density 0.004%

    No Known Activations