© 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. 4-LLAMASCOPE-RES-32K
    11. 2862
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the desire to create solutions or enhancements for various needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iationException
    -0.16
    ilion
    -0.15
    .hibernate
    -0.15
     zav
    -0.15
    .scalablytyped
    -0.15
    llib
    -0.14
    unter
    -0.14
    usan
    -0.14
    unte
    -0.14
    ounce
    -0.14
    POSITIVE LOGITS
    --+
    0.16
     Inherits
    0.15
     Executive
    0.15
     glo
    0.14
     Ã
    0.14
     Ranked
    0.14
     Allan
    0.13
    ÄĽr
    0.13
    swer
    0.13
     EXEC
    0.13
    Activations Density 0.570%

    No Known Activations