INDEX

Explanations

phrases that indicate requests or actions related to the word "to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.16

inand

-0.15

 Surround

-0.15

defgroup

-0.14

Ã¶rt

-0.14

REA

-0.14

yling

-0.14

.opens

-0.14

atsby

-0.14

POSITIVE LOGITS

 Ronald

0.15

rud

0.15

 Cumhuriyet

0.14

hton

0.14

 Cord

0.14

($('<

0.13

©

0.13

urr

0.13

ÐµÐ¹Ð½

0.13

Å¡ÃŃ

0.13

Activations Density 0.016%

phrases that indicate requests or actions related to the word "to."

No Comments

No Known Activations