INDEX

Explanations

phrases related to organizations and groups, particularly in the context of competitions and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

bam

-0.15

:)↵

-0.15

bilt

-0.14

orado

-0.14

 Cone

-0.14

 Rapids

-0.14

peater

-0.14

'],$_

-0.14

bud

-0.13

terdam

-0.13

POSITIVE LOGITS

](

0.35

"](

0.32

ãĢįï¼Ī

0.31

'](

0.31

`](

0.27

ãĢĭï¼Ī

0.27

ï¼īï¼Ī

0.25

ãĢıï¼Ī

0.25

([

0.24

#endif

0.23

Activations Density 0.466%

phrases related to organizations and groups, particularly in the context of competitions and achievements

No Comments

No Known Activations