© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 19-LLAMASCOPE-RES-32K
    11. 32302
    Prev
    Next
    INDEX
    Explanations

    references to methods or options in a procedural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hof
    -0.15
    kova
    -0.14
    aul
    -0.14
    ijd
    -0.14
    ledge
    -0.14
     anders
    -0.14
    ãģ¯ãģļ
    -0.14
    anza
    -0.13
    ways
    -0.13
    imer
    -0.13
    POSITIVE LOGITS
     most
    0.35
     ê°Ģìŀ¥
    0.26
    most
    0.26
     наиболее
    0.25
     MOST
    0.24
     सबस
    0.24
    _most
    0.23
    -most
    0.23
     Most
    0.22
    æľĢ
    0.21
    Activations Density 0.018%

    No Known Activations