INDEX

Explanations

phrases indicating ongoing or current actions and states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 thumbs

-0.15

abar

-0.15

-0.14

Ã¶l

-0.14

Ã©d

-0.14

uen

-0.14

EMU

-0.13

oup

-0.13

POSITIVE LOGITS

 entering

0.47

 enters

0.45

 enter

0.45

enter

0.45

 Enter

0.40

Entering

0.39

-enter

0.38

Enter

0.38

è¿Ľåħ¥

0.37

 ENTER

0.37

Activations Density 0.107%

phrases indicating ongoing or current actions and states

No Comments

No Known Activations