INDEX

Explanations

network-related terms and concepts

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

iscard

-0.17

enburg

-0.16

NOR

-0.15

enth

-0.14

ÑĩÑĥÐº

-0.14

gee

-0.14

 Ð½Ð¾ÑĢ

-0.14

.hot

-0.13

ittal

-0.13

POSITIVE LOGITS

/Private

0.15

vp

0.15

ikel

0.14

Ø¨Ø§ØŃ

0.14

 Charm

0.14

jsx

0.14

YTE

0.13

ë°ķ

0.13

aaS

0.13

pert

0.13

Activations Density 0.039%

network-related terms and concepts

No Comments

No Known Activations