© 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 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. 16-LLAMASCOPE-RES-32K
    11. 19944
    Prev
    Next
    INDEX
    Explanations

    references to vehicle types and specifications, particularly hybrids and comparisons with traditional models

    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
     Bast
    -0.16
     aspect
    -0.16
     aspects
    -0.15
    (s
    -0.14
    urdu
    -0.14
     a
    -0.14
     Loose
    -0.14
     via
    -0.14
     Ner
    -0.14
     or
    -0.13
    POSITIVE LOGITS
     ëĮĢë¶Ģë¶Ħ
    0.18
    _stylesheet
    0.17
     moden
    0.17
     болÑĮÑĪин
    0.16
     typical
    0.15
    pell
    0.15
     moderne
    0.15
    vens
    0.15
     ÑģÑĥÑĩаÑģ
    0.15
     meisten
    0.14
    Activations Density 0.219%

    No Known Activations