INDEX

Explanations

phrases indicating quantities or counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

CRET

-0.14

/apt

-0.13

cud

-0.13

 Ð¿ÐµÑĢÐµÐ¿

-0.13

 base

-0.13

icot

-0.13

æķ´ä¸ª

-0.13

ust

-0.13

turnstile

-0.13

.Accessible

-0.13

POSITIVE LOGITS

 different

0.17

 dozen

0.15

EVT

0.15

different

0.15

 dalÅ¡ÃŃch

0.14

eraÃ§Ã£o

0.14

 sclerosis

0.14

adder

0.14

allis

0.14

tdown

0.14

Activations Density 0.027%

phrases indicating quantities or counts

No Comments

No Known Activations