INDEX

Explanations

dialogue or conversational elements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

guy

-0.21

 dudes

-0.20

 dude

-0.19

 guys

-0.19

 Guys

-0.17

"Yeah

-0.16

hey

-0.15

aget

-0.15

Hey

-0.15

braco

-0.15

POSITIVE LOGITS

sir

0.32

Sir

0.24

Sir

0.22

erm

0.19

åħĪçĶŁ

0.16

er

0.16

um

0.16

uh

0.16

 ladies

0.15

æĤ¨çļĦ

0.15

Activations Density 0.384%

dialogue or conversational elements in the text

No Comments

No Known Activations