INDEX

Explanations

proper nouns, particularly names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

åĩĢ

-0.15

_FATAL

-0.14

ãĤ¤ãĥĪ

-0.14

.lp

-0.14

\")

-0.13

forming

-0.13

ãĥ¼ãĥĪ

-0.13

 Means

-0.13

achuset

-0.13

"<<

-0.13

POSITIVE LOGITS

Contrib

0.23

 Contributor

0.23

Â·

0.22

 CONTRIBUT

0.22

0.20

âĢ¢

0.20

@@

0.19

By

0.19

Activations Density 0.055%

proper nouns, particularly names

No Comments

No Known Activations