© 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. 30-LLAMASCOPE-RES-32K
    11. 16876
    Prev
    Next
    INDEX
    Explanations

    dates and significant events related to public gatherings or causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oct
    -0.29
     oct
    -0.28
     Jul
    -0.28
    /oct
    -0.27
    Sep
    -0.27
    -Oct
    -0.27
     sept
    -0.27
    Oct
    -0.27
     JUL
    -0.27
     Halloween
    -0.26
    POSITIVE LOGITS
     March
    1.05
    March
    0.98
     march
    0.85
     marches
    0.62
     marched
    0.57
     marching
    0.55
     маÑĢÑĤа
    0.50
     marzo
    0.49
     Mär
    0.47
     February
    0.44
    Activations Density 0.257%

    No Known Activations