INDEX

Explanations

expressions of uncertainty or questioning statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 ÐŁÑĢÐ°

-0.14

.ua

-0.14

/km

-0.14

Ã¢r

-0.14

anim

-0.13

Ã¼rn

-0.13

ocache

-0.13

åı¸

-0.13

Checksum

-0.13

POSITIVE LOGITS

 exactly

0.15

ipt

0.15

zia

0.15

Ø§Ø«

0.15

ipl

0.14

west

0.13

à¤¾à¤°à¤£

0.13

enses

0.13

zb

0.13

Activations Density 0.042%

expressions of uncertainty or questioning statements

No Comments

No Known Activations