INDEX

Explanations

terms related to the environment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

eria

-0.17

er

-0.17

ekim

-0.17

ÃŃcul

-0.15

bum

-0.15

ÑĤÐ¸Ðº

-0.15

ifter

-0.14

hua

-0.14

ÑĢÐ°Ð²Ð¸

-0.14

ecz

-0.14

POSITIVE LOGITS

IRONMENT

0.32

IRON

0.25

iro

0.25

oyer

0.25

lope

0.24

iable

0.23

ying

0.23

oron

0.23

ornment

0.21

iros

0.20

Activations Density 0.007%

terms related to the environment

No Comments

No Known Activations