INDEX

Explanations

phrases that emphasize historical significance and context

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

 minul

-0.15

compat

-0.15

 forthcoming

-0.14

 Recently

-0.14

chedulers

-0.14

è¨

-0.14

.DataType

-0.14

dw

-0.14

ÑĮÐ¾Ð¼Ñĥ

-0.14

 yÄ±ldÄ±r

-0.13

POSITIVE LOGITS

 later

0.29

 legend

0.25

 eventually

0.23

later

0.22

Eventually

0.21

 Later

0.20

 Eventually

0.20

 modern

0.19

Later

0.18

 spÃ¤ter

0.18

Activations Density 0.221%

phrases that emphasize historical significance and context

No Comments

No Known Activations