INDEX

Explanations

verbs indicating change or action

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

.fm

-0.17

abi

-0.15

obi

-0.15

prak

-0.15

abyrin

-0.14

.sponge

-0.14

.openConnection

-0.14

á»ĳt

-0.14

 destinationViewController

-0.14

adele

-0.14

POSITIVE LOGITS

0.16

Mim

0.15

?page

0.15

0.14

 Crack

0.14

 faithful

0.13

tual

0.13

grp

0.13

ija

0.13

Activations Density 0.029%

verbs indicating change or action

No Known Activations