© 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. 17688
    Prev
    Next
    INDEX
    Explanations

    nested structures in mathematical notations or expressions

    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
    >
    -0.38
    }
    -0.38
    {{
    -0.28
    ãģ¨
    -0.26
    ãģ¨ãģĹãģ¦
    -0.25
    ãģ¨ãģĦãģĨ
    -0.24
    ãģ¨ãĤĤ
    -0.23
    ãĤĴ
    -0.22
    ãģ¨ãģĻãĤĭ
    -0.21
    {{{
    -0.21
    POSITIVE LOGITS
    âĸį
    0.22
    ãĥ¼ãĥĩ
    0.15
    मत
    0.15
    ernel
    0.14
    ernals
    0.14
    rais
    0.14
    elez
    0.14
    okin
    0.13
    çļĦå£°éŁ³
    0.13
    anas
    0.13
    Activations Density 0.055%

    No Known Activations