INDEX

Explanations

references to numerical values, comments, and expressions of strong opinion or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.YesNo

-0.16

leaf

-0.16

-0.14

 oblig

-0.14

cin

-0.14

 Downs

-0.14

.ob

-0.14

\Resources

-0.14

adera

-0.14

íĺ¸

-0.14

POSITIVE LOGITS

abbr

0.15

Ð¸ÑĩÐ½Ð¸Ð¹

0.15

ugs

0.15

ÙĬØ¯Ø§

0.15

Fab

0.14

Rug

0.14

htm

0.14

 fore

0.14

.Debugger

0.14

ses

0.14

Activations Density 0.000%

references to numerical values, comments, and expressions of strong opinion or emphasis

No Comments

No Known Activations