© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28-LLAMASCOPE-RES-32K
    11. 28104
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and user interaction in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ïĥία
    -0.13
    ãģ®ãģ¯
    -0.12
    ï¼ĮåIJĮæŶ
    -0.12
    izzo
    -0.12
    ãģªãģı
    -0.12
     داخ
    -0.12
    ãģĵãģ¨ãģ¯
    -0.11
    ало
    -0.11
    ongyang
    -0.11
     внеÑģ
    -0.11
    POSITIVE LOGITS
     where
    1.33
    where
    1.06
     Where
    0.97
    _where
    0.91
     donde
    0.91
    Where
    0.89
    	where
    0.89
     où
    0.88
     WHERE
    0.86
     где
    0.83
    Activations Density 2.057%

    No Known Activations