© 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. 10-LLAMASCOPE-RES-32K
    11. 23760
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to physics and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    town
    -0.15
    ãĥ©ãĥ¼
    -0.14
    ras
    -0.14
    rm
    -0.14
    fu
    -0.14
    ssc
    -0.14
    à¹ģรà¸ĩ
    -0.14
    éģĵ
    -0.14
    _MODULE
    -0.14
    vinc
    -0.14
    POSITIVE LOGITS
    cope
    0.18
     Strand
    0.15
     Lauderdale
    0.14
    lots
    0.13
    ابÙĤÙĩ
    0.13
    cke
    0.13
    ìłģìľ¼ë¡ľ
    0.13
    classname
    0.13
    ìĦĿ
    0.13
     envy
    0.13
    Activations Density 0.923%

    No Known Activations