© 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. 20-LLAMASCOPE-RES-32K
    11. 22533
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms related to debt and funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    evi
    -0.15
    hiba
    -0.15
    faf
    -0.15
    raman
    -0.14
    vida
    -0.14
    okie
    -0.14
    entar
    -0.14
    apsed
    -0.14
    icari
    -0.14
    åĪ
    -0.14
    POSITIVE LOGITS
     frequ
    0.28
     occupied
    0.27
     enjoyed
    0.27
     shared
    0.26
     owned
    0.25
     possessed
    0.24
     worn
    0.23
    shared
    0.23
     inhabited
    0.21
    owned
    0.20
    Activations Density 0.373%

    No Known Activations