© 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. 16-LLAMASCOPE-RES-32K
    6. 7115
    Prev
    Next
    INDEX
    Explanations

    references to recognized organizations, figures, or concepts in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alars
    -0.18
    تبÙĩ
    -0.15
    574
    -0.14
    estring
    -0.14
    hue
    -0.14
    ::<
    -0.14
    ÑĩаÑģ
    -0.14
    pref
    -0.14
    é²ľ
    -0.13
    agara
    -0.13
    POSITIVE LOGITS
     etc
    0.82
    etc
    0.69
     among
    0.61
    çŃī
    0.55
     amongst
    0.54
    among
    0.54
    ãģªãģ©
    0.49
     çŃī
    0.48
     ëĵ±
    0.45
     ÑĤоÑīо
    0.44
    Activations Density 0.455%

    No Known Activations