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. 28-LLAMASCOPE-RES-32K
    6. 532
    Prev
    Next
    INDEX
    Explanations

    critical commentary on sports performance and strategy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kate
    -0.18
     infield
    -0.16
     batting
    -0.16
    iod
    -0.16
    inha
    -0.15
    äge
    -0.15
     innings
    -0.15
    ICES
    -0.15
     inning
    -0.14
     Blackhawks
    -0.14
    POSITIVE LOGITS
     NFL
    0.35
     football
    0.35
     Football
    0.32
    Football
    0.29
    NFL
    0.29
     Week
    0.28
     NFC
    0.26
    football
    0.26
    QB
    0.25
     Sundays
    0.25
    Activations Density 0.391%

    No Known Activations