INDEX

Explanations

predictions or future intentions expressed through the word "will."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Ling

-0.15

esser

-0.14

ement

-0.14

 land

-0.14

emotion

-0.14

ystone

-0.14

illo

-0.14

land

-0.14

ements

-0.13

cobra

-0.13

POSITIVE LOGITS

weis

0.15

etÃŃ

0.14

&page

0.14

renom

0.14

egov

0.14

ominator

0.14

.IContainer

0.14

zig

0.13

-variable

0.13

agu

0.13

Activations Density 0.050%

predictions or future intentions expressed through the word "will."

No Comments

No Known Activations