INDEX

Explanations

phrases related to upcoming events and future updates

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

trak

-0.15

lar

-0.15

arde

-0.15

illard

-0.15

ç¯

-0.14

ey

-0.14

Aspect

-0.14

standen

-0.14

ObjectContext

-0.14

aste

-0.14

POSITIVE LOGITS

 Conv

0.16

 å£

0.16

ãĥ³ãĥĨãĤ£

0.15

nap

0.15

-fontawesome

0.15

dum

0.14

moil

0.14

idable

0.14

ahat

0.14

conv

0.14

Activations Density 0.063%

phrases related to upcoming events and future updates

No Comments

No Known Activations