© 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. 25-LLAMASCOPE-RES-32K
    11. 21480
    Prev
    Next
    INDEX
    Explanations

    keywords related to policy changes and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    еÑģÑĤÑĮ
    -0.13
    ëĭĺ
    -0.13
    ิà¹Ĥà¸Ļ
    -0.13
    ÙĪÙĨÙĩ
    -0.12
    urn
    -0.12
    _OLD
    -0.12
     analogy
    -0.12
    oley
    -0.12
    voir
    -0.12
    182
    -0.11
    POSITIVE LOGITS
     that
    0.63
    that
    0.57
     which
    0.47
     whose
    0.44
    	that
    0.43
     rằng
    0.39
    which
    0.39
    _that
    0.38
     Ú©Ùĩ
    0.38
     hogy
    0.37
    Activations Density 2.424%

    No Known Activations