© 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. 9-LLAMASCOPE-RES-32K
    11. 26485
    Prev
    Next
    INDEX
    Explanations

    connections and structural components in mechanical assembly descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naz
    -0.17
    NullException
    -0.16
    Ñĥда
    -0.15
    دا
    -0.15
    OrFail
    -0.14
    á»Ĺ
    -0.14
    lý
    -0.14
    िषय
    -0.14
    pageTitle
    -0.14
    _MACHINE
    -0.14
    POSITIVE LOGITS
     hem
    0.15
    lect
    0.15
    kees
    0.15
    æ
    0.15
     Sidney
    0.14
    麻
    0.14
    âĨ
    0.14
    itches
    0.14
    rack
    0.14
     Prometheus
    0.14
    Activations Density 0.160%

    No Known Activations