© 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. 18520
    Prev
    Next
    INDEX
    Explanations

    technical details related to networking services and specifications

    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
     mate
    -0.16
     mates
    -0.15
    uxe
    -0.14
     Kut
    -0.14
     traffic
    -0.14
     device
    -0.14
    uptime
    -0.14
    thro
    -0.14
     station
    -0.14
     devices
    -0.14
    POSITIVE LOGITS
    fiber
    0.21
     ethernet
    0.21
     fibre
    0.20
     fiber
    0.20
    802
    0.19
    ä¹Ļ
    0.19
     Ethernet
    0.19
     cellular
    0.18
    _SERIAL
    0.18
    eth
    0.18
    Activations Density 0.180%

    No Known Activations