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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 13-LLAMASCOPE-RES-32K
    11. 18729
    Prev
    Next
    INDEX
    Explanations

    references to musical artists, songs, and albums throughout various time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    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
    -0.20
    200
    -0.17
     Bush
    -0.17
    190
    -0.17
     Victorian
    -0.16
    Bush
    -0.15
     wireless
    -0.15
     dot
    -0.14
    abo
    -0.14
    xmm
    -0.14
    POSITIVE LOGITS
    197
    0.33
    196
    0.32
    ï¼ĪæĺŃåĴĮ
    0.23
     USSR
    0.21
    Û±Û¹Û·
    0.21
    Û±Û¹Û¶
    0.19
     Soviet
    0.19
    195
    0.18
     Beatles
    0.18
    tape
    0.18
    Activations Density 0.653%

    No Known Activations