© 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. 17-LLAMASCOPE-RES-32K
    11. 27204
    Prev
    Next
    INDEX
    Explanations

    constructs related to qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Türkiye
    -0.16
    DataRow
    -0.14
    isku
    -0.13
    ục
    -0.13
    cobra
    -0.13
     Tow
    -0.13
    ConfigurationException
    -0.13
    ê´Ģ
    -0.13
    Ä°stanbul
    -0.13
    borg
    -0.13
    POSITIVE LOGITS
     tale
    0.19
     mix
    0.18
     blend
    0.17
    åħ¥ãĤĬ
    0.15
     Lesson
    0.15
    гал
    0.14
    PELL
    0.14
     dap
    0.14
    ysz
    0.13
    brero
    0.13
    Activations Density 0.197%

    No Known Activations