INDEX

Explanations

references to follow-up actions or discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

.ToolTip

-0.16

Ø§Ø¶

-0.15

ninger

-0.15

uts

-0.14

iete

-0.14

Äįky

-0.14

ieten

-0.14

ubi

-0.14

uli

-0.13

à¸Ļà¸³

-0.13

POSITIVE LOGITS

 follow

0.34

 Follow

0.31

Follow

0.29

.follow

0.28

follow

0.27

-follow

0.25

_follow

0.21

 follows

0.20

-up

0.19

 FOLLOW

0.19

Activations Density 0.007%

references to follow-up actions or discussions

No Comments

No Known Activations