© 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. 29-LLAMASCOPE-RES-32K
    11. 1999
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    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¯
    -0.13
    izzo
    -0.12
    ãģĵãģ¨ãģ¯
    -0.12
    ï¼ĮåIJĮæŶ
    -0.12
    ало
    -0.11
    ãģªãģı
    -0.11
    ìĶ©
    -0.11
     Enumerator
    -0.11
    ãģ¯ãģļ
    -0.11
    POSITIVE LOGITS
     where
    1.30
    where
    1.04
     Where
    0.95
    _where
    0.89
     donde
    0.89
    	where
    0.87
    Where
    0.86
     où
    0.86
     WHERE
    0.84
     где
    0.81
    Activations Density 2.019%

    No Known Activations