© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 19437
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics and player performance metrics

    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
    ãĥ¼ãĥľ
    -0.14
    ersh
    -0.14
    AndGet
    -0.14
    arget
    -0.13
    ÛĮست
    -0.13
    qui
    -0.13
    past
    -0.13
     Past
    -0.13
     defeat
    -0.13
     defeated
    -0.13
    POSITIVE LOGITS
     split
    0.19
    ModelProperty
    0.17
    IDA
    0.17
     while
    0.17
     appearances
    0.16
    -split
    0.15
    Spread
    0.15
     jadx
    0.15
     Appearance
    0.15
    erez
    0.15
    Activations Density 0.037%

    No Known Activations