© 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. 30-LLAMASCOPE-RES-32K
    11. 4083
    Prev
    Next
    INDEX
    Explanations

    specific terms related to gaming mechanics and their impact on gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cubes
    -0.18
     cube
    -0.16
    auer
    -0.15
     cub
    -0.15
    Cube
    -0.14
    ichel
    -0.14
     Cub
    -0.14
    .fold
    -0.14
    èĭ¹æŀľ
    -0.14
    losed
    -0.14
    POSITIVE LOGITS
     interior
    0.21
     inner
    0.21
    inner
    0.20
    åĨħ
    0.19
     Broad
    0.19
     Wid
    0.19
     partitions
    0.19
    åħ§
    0.18
    width
    0.18
    Broad
    0.18
    Activations Density 0.032%

    No Known Activations