INDEX

Explanations

dates and years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ø¹ÛĮ

-0.15

oki

-0.15

iston

-0.14

 dashes

-0.14

Wed

-0.14

 each

-0.14

jan

-0.14

lem

-0.14

Maj

-0.14

loquent

-0.13

POSITIVE LOGITS

.bundle

0.15

 Redistributions

0.15

$$$$

0.15

]={↵

0.14

ongo

0.14

TextStyle

0.14

esin

0.14

 spare

0.14

Activations Density 0.019%

dates and years

No Comments

No Known Activations