© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 17411
    Prev
    Next
    INDEX
    Explanations

    phrases related to microbiological effects and food preservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erald
    -0.15
    agle
    -0.15
    illos
    -0.14
    ippo
    -0.14
    rypton
    -0.14
    chrome
    -0.13
    alim
    -0.13
    _EXPORT
    -0.13
    wishlist
    -0.13
    ãĤ¸
    -0.13
    POSITIVE LOGITS
     cultures
    0.38
     fermentation
    0.38
     ferment
    0.38
     yeast
    0.37
     ye
    0.35
     culture
    0.35
     starter
    0.33
     fermented
    0.32
     Fer
    0.31
     strains
    0.30
    Activations Density 0.095%

    No Known Activations