INDEX

Explanations

references to COVID-19

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

}elseif

-0.16

oun

-0.15

adows

-0.15

 Ð·Ð¾Ð²

-0.14

-0.13

istrovstvÃŃ

-0.13

iu

-0.13

esses

-0.13

 goodwill

-0.13

Ð±Ð¾

-0.13

POSITIVE LOGITS

ãĥĥãĥĹ

0.15

zon

0.15

anye

0.15

Ãµi

0.14

Ã¶s

0.14

tings

0.14

Ã¦nd

0.14

IMER

0.14

.bpm

0.13

andard

0.13

Activations Density 0.002%

references to COVID-19

No Comments

No Known Activations