INDEX

Explanations

references to various issues and concerns, especially those labeled as "issue 9."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

àµįà´

-0.17

Ø´ÙĨ

-0.15

uren

-0.15

IENT

-0.15

ulas

-0.15

Ø®Ø§ÙĨÙĩ

-0.14

unk

-0.14

uyu

-0.14

shake

-0.14

bol

-0.14

POSITIVE LOGITS

atics

0.16

 forth

0.15

 raised

0.15

.slim

0.15

-spot

0.14

olated

0.14

ubber

0.14

iterate

0.14

Activations Density 0.044%

references to various issues and concerns, especially those labeled as "issue 9."

No Comments

No Known Activations