© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 2805
    Prev
    Next
    INDEX
    Explanations

    terms related to virtual reality hardware and its performance

    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
    ÙħÙĦ
    -0.18
    yntax
    -0.15
    воÑİ
    -0.15
    ANI
    -0.15
     Bakan
    -0.15
    ignum
    -0.14
     Hava
    -0.14
    Ø®ÛĮ
    -0.13
    íļį
    -0.13
    jav
    -0.13
    POSITIVE LOGITS
     Rift
    0.40
     Oculus
    0.39
     VR
    0.36
     Vive
    0.36
     headset
    0.32
    VR
    0.31
     vr
    0.29
     rift
    0.29
     HTC
    0.28
     virtual
    0.26
    Activations Density 0.024%

    No Known Activations