INDEX

Explanations

directions and route information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

okus

-0.20

ewe

-0.16

opr

-0.16

adders

-0.14

ÑģÐ¾Ð²

-0.14

.today

-0.14

ibus

-0.14

 vÃŃde

-0.13

fst

-0.13

ruk

-0.13

POSITIVE LOGITS

 turn

0.24

 follow

0.23

 Turn

0.22

gnore

0.22

turn

0.20

 Follow

0.19

(turn

0.18

 TURN

0.18

Turn

0.18

 slight

0.18

Activations Density 0.033%

directions and route information

No Comments

No Known Activations