INDEX

Explanations

phrases involving the word "to" that suggest actions or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.gov

-0.15

agens

-0.14

 Ð·ÐµÐ¼Ð»Ñı

-0.14

MinMax

-0.14

xdc

-0.14

ÙĦÙĬÙģ

-0.14

_DAC

-0.14

ifiers

-0.14

mad

-0.14

-eyed

-0.13

POSITIVE LOGITS

¼åĲĪ

0.18

ÙĪØ§Ùĩ

0.16

hac

0.15

weis

0.15

ubl

0.15

ãĥ¼ãĥī

0.14

 solic

0.14

onga

0.14

åĩ

0.14

ilo

0.13

Activations Density 0.479%

phrases involving the word "to" that suggest actions or instructions

No Comments

No Known Activations