INDEX

Explanations

phrases indicating variability or dependence on different factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

rouw

-0.16

Ã¥n

-0.16

ÙĪØ¬ÙĪØ¯

-0.14

artz

-0.14

egral

-0.14

uttle

-0.14

 Ø¨Ø§ÛĮ

-0.14

Should

-0.14

 seins

-0.14

 Should

-0.13

POSITIVE LOGITS

 depending

0.17

onga

0.15

ouse

0.14

 è¢

0.14

BCM

0.14

itere

0.14

depending

0.14

apor

0.13

KeyId

0.13

typed

0.13

Activations Density 0.065%

phrases indicating variability or dependence on different factors

No Comments

No Known Activations

phrases indicating variability or dependence on different factors

No Comments

No Known Activations