INDEX

Explanations

terms related to systems and industries impacting human activity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ieren

-0.17

lich

-0.15

allen

-0.15

Ã¶l

-0.14

ataka

-0.14

zano

-0.14

etch

-0.14

odor

-0.14

arih

-0.14

POSITIVE LOGITS

 itself

0.24

ÐŁÐļ

0.16

.onViewCreated

0.16

iest

0.15

 writ

0.15

osphere

0.15

liest

0.15

 proper

0.14

 Ø§ÙĦØ¬Ø¯ÙĬØ¯

0.14

åıĬåħ¶

0.14

Activations Density 0.189%

terms related to systems and industries impacting human activity

No Comments

No Known Activations