© 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. 14-LLAMASCOPE-RES-32K
    11. 13871
    Prev
    Next
    INDEX
    Explanations

    terms related to the publishing process and challenges faced by authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alles
    -0.16
    ebo
    -0.16
    podob
    -0.16
    ucci
    -0.14
    elong
    -0.14
    ylland
    -0.14
    erus
    -0.13
    ilden
    -0.13
     Cob
    -0.13
    assel
    -0.13
    POSITIVE LOGITS
     Scre
    0.16
    holm
    0.14
     Successful
    0.14
    clone
    0.13
    uede
    0.13
    MZ
    0.13
    ÙĦÙħÙĩ
    0.13
    ä¼ģ
    0.13
    -market
    0.13
     Investment
    0.13
    Activations Density 0.015%

    No Known Activations