INDEX

Explanations

terminology related to dialogue systems and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

yntax

-0.15

áº»

-0.15

languages

-0.14

 oper

-0.14

ãĥĥãĥĹ

-0.14

èĥŀ

-0.14

/sweetalert

-0.14

'field

-0.14

awan

-0.13

nea

-0.13

POSITIVE LOGITS

 utter

0.25

utter

0.20

 grounding

0.20

 novel

0.19

 Novel

0.18

 paraph

0.15

 rated

0.14

oulder

0.14

osti

0.14

 entail

0.14

Activations Density 0.022%

terminology related to dialogue systems and their components

No Comments

No Known Activations