INDEX

Explanations

phrases indicating a sense of belonging or community

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ayacak

-0.16

.lb

-0.15

.nr

-0.15

hrad

-0.14

åĢĴ

-0.14

Ø§Ø±ÛĮ

-0.14

ays

-0.13

èĤ¯

-0.13

.openConnection

-0.13

Selectable

-0.13

POSITIVE LOGITS

0.15

!=(

0.15

oss

0.15

urg

0.14

OMEM

0.13

orum

0.13

 Sunder

0.13

iben

0.13

amus

0.13

 quot

0.13

Activations Density 0.013%

phrases indicating a sense of belonging or community

No Comments

No Known Activations