© 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. 7-LLAMASCOPE-RES-32K
    11. 5502
    Prev
    Next
    INDEX
    Explanations

    terminology related to crowdfunding and fundraising platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Citation
    -0.16
    ssel
    -0.16
    ï¸
    -0.15
    à¸Ļว
    -0.15
    unger
    -0.14
    ichten
    -0.14
     ÑĢев
    -0.14
    à¥įà¤Łà¤°
    -0.13
    ield
    -0.13
    wiki
    -0.13
    POSITIVE LOGITS
    empo
    0.15
    UBLE
    0.15
    ighton
    0.14
     filib
    0.14
     Milit
    0.13
    رÙĪÛĮ
    0.13
     thất
    0.13
    Ñľ
    0.13
     Bened
    0.13
    ennes
    0.13
    Activations Density 0.011%

    No Known Activations