INDEX

Explanations

mentions of runners and various references to the word "killer."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ing

-0.22

edList

-0.20

ers

-0.18

avid

-0.17

Pure

-0.16

ning

-0.16

anto

-0.16

able

-0.16

elman

-0.15

ible

-0.15

POSITIVE LOGITS

-upper

0.20

ama

0.17

idge

0.17

cury

0.16

.RunWith

0.15

 faint

0.15

udden

0.15

beros

0.15

Î¼Î¿ÏĤ

0.15

-than

0.15

Activations Density 0.087%

mentions of runners and various references to the word "killer."

No Comments

No Known Activations