© 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. 31-LLAMASCOPE-RES-32K
    11. 31627
    Prev
    Next
    INDEX
    Explanations

    code-related elements, particularly in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ëĭ¤ìļ´ë°Ľê¸°
    -0.14
     íĮĮìĿ¼ì²¨ë¶Ģ
    -0.13
     JsonRequest
    -0.13
     ëĦ¤ìĿ´íĬ¸
    -0.12
     ë¹Ħë°Ģê¸Ģ
    -0.12
     ydk
    -0.11
    Ãło
    -0.11
     MEDIATEK
    -0.11
     HTTPS
    -0.11
     __________________↵↵
    -0.11
    POSITIVE LOGITS
     delta
    0.23
     offset
    0.23
     distance
    0.21
     offsets
    0.21
     length
    0.21
     scale
    0.21
     range
    0.20
     pos
    0.20
     min
    0.20
     width
    0.20
    Activations Density 1.454%

    No Known Activations