INDEX

Explanations

specific numerical values and business-related terms in the context of transactions or data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

yla

-0.15

udson

-0.15

 Borg

-0.15

PTR

-0.15

 è´

-0.15

ÑĥÐ´Ð°

-0.13

ucs

-0.13

è²

-0.13

_CLOSE

-0.13

 Pointer

-0.13

POSITIVE LOGITS

 drop

0.20

(drop

0.19

.drop

0.17

-drop

0.17

 Drop

0.16

drop

0.16

 DROP

0.16

 conc

0.15

Fol

0.15

ÙģÙĤ

0.15

Activations Density 0.021%

specific numerical values and business-related terms in the context of transactions or data

No Comments

No Known Activations