INDEX

Explanations

phrases related to navigating or progressing through situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ltk

-0.22

 Harness

-0.16

lint

-0.15

toupper

-0.14

adium

-0.14

 Timing

-0.14

 headline

-0.14

edback

-0.14

STA

-0.14

fat

-0.14

POSITIVE LOGITS

 rabbit

0.28

 aisle

0.27

 Rabbit

0.23

 chute

0.22

 drain

0.21

 hall

0.21

rabbit

0.21

 alley

0.21

 road

0.21

 tubes

0.21

Activations Density 0.029%

phrases related to navigating or progressing through situations

No Comments

No Known Activations