INDEX

Explanations

terms that indicate something is no longer current or relevant, specifically those related to outdated or obsolete concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.17

 turn

-0.16

 Cent

-0.16

cur

-0.16

-0.15

 turned

-0.15

DNA

-0.15

POSITIVE LOGITS

.RunWith

0.15

ÐµÐºÐ¾

0.15

irm

0.15

ablish

0.15

ycop

0.15

\/\/

0.15

ostÃŃ

0.15

¶Ī

0.14

afil

0.14

gui

0.14

Activations Density 0.003%

terms that indicate something is no longer current or relevant, specifically those related to outdated or obsolete concepts

No Comments

No Known Activations