INDEX

Explanations

references to lists and their contents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Solve

-0.16

 Calculate

-0.12

angkan

-0.12

à¸¸à¸Ĥ

-0.12

Ð°Ð½ÑģÐ¾Ð²

-0.12

aget

-0.11

HeaderCode

-0.11

 soutÄĽ

-0.11

ĶĦ

-0.11

ÄĽla

-0.11

POSITIVE LOGITS

 list

1.27

 List

1.01

list

0.98

 lists

0.95

_list

0.86

.list

0.85

åĪĹè¡¨

0.85

List

0.85

-list

0.84

 lista

0.82

Activations Density 0.375%

references to lists and their contents

No Comments

No Known Activations