INDEX

Explanations

requests for detailed information or lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ø±Ø³ÛĮ

-0.15

ãĥ³ãĥĸ

-0.14

rawn

-0.14

unde

-0.13

orious

-0.13

term

-0.13

ÑĥÐ´

-0.13

&[

-0.13

\system

-0.13

.IsEnabled

-0.12

POSITIVE LOGITS

 below

0.74

below

0.57

 Below

0.54

Below

0.53

ä»¥ä¸ĭ

0.49

 BELOW

0.48

 abaixo

0.47

 Ð½Ð¸Ð¶Ðµ

0.47

ä¸ĭ

0.43

 ìķĦëŀĺ

0.42

Activations Density 0.171%

requests for detailed information or lists

No Comments

No Known Activations