INDEX

Explanations

directional instructions and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.17

adder

-0.16

adders

-0.15

Ð¾Ð·Ð²

-0.14

uÅŁ

-0.14

dq

-0.13

.today

-0.13

ibus

-0.13

 elsewhere

-0.13

 nearby

-0.13

POSITIVE LOGITS

 bear

0.23

Proceed

0.21

 proceed

0.21

 follow

0.21

 stay

0.20

 slight

0.20

 Proceed

0.20

bear

0.20

 turn

0.20

 staying

0.19

Activations Density 0.047%

directional instructions and locations

No Comments

No Known Activations