INDEX

Explanations

references to weight and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 exposure

-0.16

 speeches

-0.15

band

-0.15

 Processing

-0.14

wid

-0.14

wide

-0.14

ste

-0.14

Ïį

-0.14

-0.13

 reve

-0.13

POSITIVE LOGITS

 weight

0.47

 Weight

0.41

 weights

0.41

weight

0.39

Weight

0.38

 weigh

0.37

-weight

0.36

 WEIGHT

0.36

.weight

0.35

(weight

0.34

Activations Density 0.089%

references to weight and measurements

No Comments

No Known Activations