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

    Neuronpedia

    Jacobian LensNEW
    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. 28-LLAMASCOPE-RES-32K
    11. 20139
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics related to data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oga
    -0.18
    าà¸ļ
    -0.16
    777
    -0.15
    ULT
    -0.14
    le
    -0.13
    uda
    -0.13
    ÙĩÙĨ
    -0.13
    olution
    -0.13
    acha
    -0.13
    leen
    -0.12
    POSITIVE LOGITS
    å¹´
    0.25
     marks
    0.21
    marks
    0.20
    ëħĦëıĦ
    0.20
     ëħĦ
    0.20
     yılı
    0.20
    欧
    0.20
    ëħĦ
    0.20
    -present
    0.18
    å¹´ãģ®
    0.18
    Activations Density 0.090%

    No Known Activations