© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29609
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to aerodynamics and fluid mechanics

    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
    754
    -0.16
    ilir
    -0.15
     Competitive
    -0.15
    acle
    -0.15
    ophy
    -0.14
    arie
    -0.14
    å¾
    -0.14
     Vect
    -0.14
    /null
    -0.14
    太éĥİ
    -0.14
    POSITIVE LOGITS
    kara
    0.16
     åĴ
    0.16
    ara
    0.14
    ajan
    0.14
     sequ
    0.14
    plx
    0.14
    Ïģί
    0.14
    éĻµ
    0.14
    ureka
    0.14
    enthal
    0.13
    Activations Density 0.136%

    No Known Activations