INDEX

Explanations

phrases indicating supplementary or additional information

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

atten

-0.16

lett

-0.15

Ã½n

-0.15

Ø³Ø§ÙĨÛĮ

-0.14

«a

-0.14

ients

-0.14

Ú¯Ø±ÛĮ

-0.13

Ø§ÙĤ

-0.13

âĢŀP

-0.13

prints

-0.13

POSITIVE LOGITS

tion

0.26

nal

0.25

ition

0.20

eel

0.19

erval

0.18

ally

0.18

erdale

0.17

iton

0.17

uced

0.16

/sub

0.16

Activations Density 0.014%

phrases indicating supplementary or additional information

No Comments

No Known Activations