INDEX

Explanations

legal or regulatory terminology related to litigation and its processes

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

âĢ¦and

-0.17

âĢ¦the

-0.16

âĢ¦but

-0.16

âĢ¦it

-0.14

ierung

-0.13

hammer

-0.13

otyping

-0.13

ystack

-0.13

ÄįnÃŃm

-0.13

izm

-0.13

POSITIVE LOGITS

ä»¬

0.25

åĢĳ

0.20

ë¦°ìĿ´

0.14

remen

0.14

 Ø¹Ø²ÛĮØ²

0.14

ãĥ¼ãĥĸ

0.13

 iÃ§i

0.13

ëħ

0.12

iets

0.12

ÎµÎ¯ÏĤ

0.12

Activations Density 0.293%

legal or regulatory terminology related to litigation and its processes

No Comments

No Known Activations