INDEX

Explanations

dates and events associated with specific locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

urette

-0.17

 Pare

-0.15

 Throw

-0.15

azen

-0.14

 Valentine

-0.14

addock

-0.14

 TÃ¼rk

-0.14

 Easter

-0.14

corp

-0.14

 mnie

-0.13

POSITIVE LOGITS

ometr

0.17

ysz

0.17

 Hast

0.16

ember

0.15

©

0.15

ourd

0.15

 onViewCreated

0.14

kie

0.14

.qq

0.14

 Pandora

0.13

Activations Density 0.058%

dates and events associated with specific locations

No Comments

No Known Activations