© 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. 18-LLAMASCOPE-RES-32K
    11. 9349
    Prev
    Next
    INDEX
    Explanations

    references to symbols and flags associated with cultures or nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     é¦Ļ
    -0.16
    ummies
    -0.14
    ë¹Ī
    -0.14
    лини
    -0.14
    enko
    -0.14
    unkt
    -0.14
    amed
    -0.14
    -parse
    -0.14
    Ģìŀ¥
    -0.14
    znik
    -0.14
    POSITIVE LOGITS
     logo
    0.34
     symbol
    0.30
     flag
    0.29
    logo
    0.26
     Logo
    0.26
     insign
    0.26
     seal
    0.25
     emblem
    0.25
     logos
    0.25
    /logo
    0.25
    Activations Density 0.149%

    No Known Activations