INDEX

Explanations

HTML and JavaScript elements within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ã©g

-0.15

inh

-0.14

cko

-0.13

ãĥĩãĤ£ãĤ¢

-0.13

 Standards

-0.13

UNCTION

-0.13

bir

-0.13

sla

-0.13

fs

-0.13

 welding

-0.13

POSITIVE LOGITS

ç²Ĵ

0.15

.appspot

0.15

CEE

0.14

æ®µ

0.14

UIT

0.14

 Ø®ÙĪØ±

0.14

æŀģ

0.13

cae

0.13

 baiser

0.13

ght

0.13

Activations Density 0.010%

HTML and JavaScript elements within the document

No Comments

No Known Activations