INDEX

Explanations

phrases that indicate emerging or developing entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ken

-0.17

endif

-0.15

adar

-0.15

Ð½Ð°Ðº

-0.15

 Whip

-0.15

acher

-0.14

ched

-0.14

 upright

-0.14

Compat

-0.14

ugar

-0.14

POSITIVE LOGITS

/down

0.25

 coming

0.23

 down

0.23

-down

0.21

Coming

0.20

 comer

0.19

coming

0.19

 running

0.19

oming

0.18

down

0.18

Activations Density 0.009%

phrases that indicate emerging or developing entities

No Comments

No Known Activations