INDEX

Explanations

quantitative descriptions related to size 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

uffer

-0.16

hol

-0.15

 Spike

-0.14

.TabIndex

-0.14

 impact

-0.14

 draw

-0.14

and

-0.14

-0.13

eron

-0.13

 increment

-0.13

POSITIVE LOGITS

 size

0.48

size

0.44

å¤§å°ı

0.43

 sizes

0.42

 Size

0.41

Size

0.40

 ÑĢÐ°Ð·Ð¼ÐµÑĢ

0.38

_size

0.37

.size

0.37

 SIZE

0.37

Activations Density 0.307%

quantitative descriptions related to size and measurements

No Comments

No Known Activations