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. 11-LLAMASCOPE-RES-32K
    6. 18403
    Prev
    Next
    INDEX
    Explanations

    references to famous comedic performances and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    191
    -0.19
    200
    -0.17
    190
    -0.16
     wireless
    -0.16
    abo
    -0.16
     Victorian
    -0.15
     Wireless
    -0.15
     Bush
    -0.15
    ilia
    -0.14
    iore
    -0.14
    POSITIVE LOGITS
    197
    0.31
    196
    0.27
     USSR
    0.22
    ï¼ĪæĺŃåĴĮ
    0.22
    198
    0.20
    Û±Û¹Û·
    0.19
     Soviet
    0.19
    tape
    0.18
    Û±Û¹Û¶
    0.17
     tapes
    0.16
    Activations Density 0.906%

    No Known Activations