© 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. 29-LLAMASCOPE-RES-32K
    11. 14638
    Prev
    Next
    INDEX
    Explanations

    financial terms related to donations or benefactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odash
    -0.15
     smrt
    -0.14
     latter
    -0.14
    ograd
    -0.13
     anlamına
    -0.12
     itself
    -0.12
    apro
    -0.12
    \↵
    -0.12
    kees
    -0.12
    rox
    -0.12
    POSITIVE LOGITS
    .ISupportInitialize
    0.14
     yine
    0.13
    *)((
    0.13
     Haven
    0.12
     EITHER
    0.12
    äºŀ
    0.12
     assorted
    0.12
     ebenfalls
    0.12
    tol
    0.12
     miscellaneous
    0.12
    Activations Density 1.418%

    No Known Activations