INDEX

Explanations

various types of lists mentioned throughout the text

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

 nest

-0.17

chez

-0.15

inders

-0.15

lush

-0.15

/or

-0.15

amp

-0.14

agara

-0.14

/utility

-0.14

 Nest

-0.14

 nests

-0.13

POSITIVE LOGITS

-unstyled

0.21

.scalablytyped

0.20

icator

0.16

eners

0.16

ened

0.15

rik

0.15

owel

0.15

ento

0.15

ASIC

0.15

gnore

0.15

Activations Density 0.032%

various types of lists mentioned throughout the text

No Comments

No Known Activations