INDEX

Explanations

programmatic functions and methods related to input and output operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

fty

-0.18

áº¯c

-0.16

reek

-0.16

ulet

-0.15

efon

-0.15

Ã±

-0.14

areth

-0.14

Ð½ÑĸÐ¹

-0.14

vrier

-0.14

 æł

-0.14

POSITIVE LOGITS

¨

0.22

tons

0.21

oons

0.20

es

0.20

anks

0.19

ãĥ¼ãĤ¹

0.19

itos

0.19

º

0.19

ords

0.19

inas

0.18

Activations Density 0.280%

programmatic functions and methods related to input and output operations

No Comments

No Known Activations