INDEX

Explanations

code elements related to array processing and token manipulation

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

tons

-0.15

utsch

-0.15

untu

-0.15

 tons

-0.14

ÄĻd

-0.14

 Audience

-0.14

 Gill

-0.14

caled

-0.14

bare

-0.14

thora

-0.13

POSITIVE LOGITS

.size

0.24

 size

0.20

.length

0.19

 DropIndex

0.18

 GLsizei

0.17

 sizeof

0.17

 length

0.17

 getItemCount

0.17

=len

0.17

	sizeof

0.17

Activations Density 0.159%

code elements related to array processing and token manipulation

No Comments

No Known Activations