© 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. 15-LLAMASCOPE-RES-32K
    6. 26514
    Prev
    Next
    INDEX
    Explanations

    references to significant historical documents or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.16
    ruz
    -0.15
    лÑĥж
    -0.14
     Ø´ÙĩرÛĮ
    -0.14
    enci
    -0.14
    illion
    -0.14
    ernals
    -0.14
    ê·ľ
    -0.14
    erver
    -0.14
    .Style
    -0.14
    POSITIVE LOGITS
    179
    0.15
     Enlightenment
    0.15
     Guar
    0.15
    èįī
    0.14
     draft
    0.14
     drafted
    0.14
     delegates
    0.14
     bic
    0.14
    chor
    0.13
     drafts
    0.13
    Activations Density 0.065%

    No Known Activations