INDEX

Explanations

references to border-related topics or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ocoa

-0.17

³

-0.17

-bodied

-0.16

ç¦ıåĪ©

-0.15

 è¡ĮæĶ¿

-0.15

ãĥĬãĥ¼

-0.14

urt

-0.14

ernals

-0.14

 Preconditions

-0.14

enko

-0.14

POSITIVE LOGITS

ing

0.18

alu

0.18

gren

0.17

/back

0.16

lines

0.16

gate

0.14

(Border

0.14

less

0.14

DCF

0.14

lands

0.14

Activations Density 0.019%

references to border-related topics or issues

No Comments

No Known Activations