INDEX

Explanations

code-related structures and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 comple

-0.17

 Snyder

-0.14

 complement

-0.14

ATRIX

-0.14

UV

-0.14

 cust

-0.14

monds

-0.14

imers

-0.14

Ð¹Ð¾Ð¼

-0.13

ÑĢÐ¾ÑģÑĤ

-0.13

POSITIVE LOGITS

aya

0.17

à¤¿à¤¥

0.16

arda

0.16

.batch

0.15

elly

0.15

yard

0.14

batch

0.14

&_

0.14

 Lois

0.14

Activations Density 0.012%

code-related structures and functions

No Comments

No Known Activations