INDEX

Explanations

legal terminology and references to judicial processes or decisions

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

 tá»ĳ

-0.15

unger

-0.15

 critic

-0.15

_ASSUME

-0.14

_detect

-0.13

 memor

-0.13

á»ĩu

-0.13

suggest

-0.13

 $("#"

-0.13

hod

-0.13

POSITIVE LOGITS

 clarity

0.55

 clarification

0.48

clar

0.47

 clear

0.46

 clar

0.44

 Clar

0.43

-clear

0.43

 clarify

0.43

 clearing

0.42

.clear

0.41

Activations Density 0.304%

legal terminology and references to judicial processes or decisions

No Comments

No Known Activations