INDEX

Explanations

preprocessor directives in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

alach

-0.16

oq

-0.15

zac

-0.15

awe

-0.15

idal

-0.14

ANCH

-0.14

iffin

-0.14

unch

-0.14

 Transmission

-0.14

Äĩ

-0.13

POSITIVE LOGITS

 Tato

0.14

ÐµÑĢÐµÐ¶

0.14

ICollection

0.14

icket

0.13

urat

0.13

ãĥ£

0.13

è¾º

0.13

.contentType

0.13

nost

0.13

resh

0.13

Activations Density 0.001%

preprocessor directives in programming code

No Comments

No Known Activations