INDEX

Explanations

phrases that indicate a positive evaluation or reputation of entities or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ulan

-0.17

ÑĩÑĥ

-0.15

ÃŃses

-0.15

éĥ¡

-0.15

.parts

-0.15

sonian

-0.15

_Impl

-0.15

 langs

-0.14

com

-0.14

Ð°Ð¹ÑĤ

-0.14

POSITIVE LOGITS

Ã³

0.17

rated

0.15

 Buch

0.14

efa

0.14

gn

0.14

 Bishop

0.14

 Uncategorized

0.14

Urs

0.14

 rated

0.14

eg

0.14

Activations Density 0.086%

phrases that indicate a positive evaluation or reputation of entities or products

No Comments

No Known Activations