INDEX

Explanations

the use of dialogue and conversational elements within 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

roje

-0.14

Rig

-0.14

èĵ

-0.14

oupper

-0.14

rig

-0.14

ventions

-0.14

ningar

-0.14

loub

-0.13

igs

-0.13

 radicals

-0.13

POSITIVE LOGITS

enet

0.15

ince

0.15

iston

0.15

ä¸Ī

0.14

ictor

0.14

ikh

0.14

Fmt

0.14

 Ã©l

0.13

udder

0.13

Activations Density 0.150%

the use of dialogue and conversational elements within the text

No Comments

No Known Activations