© 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. 20-LLAMASCOPE-RES-32K
    11. 22906
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Dil" and related variations, particularly in contexts that imply dilution or comparison

    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
    i
    -0.18
    esis
    -0.16
    elli
    -0.15
    ellen
    -0.14
    ront
    -0.14
    akin
    -0.14
    ably
    -0.14
    ing
    -0.14
    CB
    -0.14
    egot
    -0.14
    POSITIVE LOGITS
     dil
    0.23
    apid
    0.22
    ution
    0.21
     Dil
    0.20
    ssel
    0.19
    uters
    0.18
    UTION
    0.17
    .infinity
    0.17
    ivery
    0.17
    usions
    0.17
    Activations Density 0.010%

    No Known Activations