INDEX

Explanations

references to "pom" variations, which may relate to food or culinary contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ã¹ng

-0.15

ndo

-0.14

 honest

-0.14

ozÃŃ

-0.14

Ú¯ÛĮØ±

-0.14

:async

-0.14

à¸µà¸¢à¸Ķ

-0.14

isty

-0.14

quent

-0.14

.getSharedPreferences

-0.14

POSITIVE LOGITS

antz

0.19

pons

0.18

Pom

0.17

acent

0.17

pos

0.17

pon

0.16

pom

0.16

oldt

0.16

etime

0.16

acea

0.16

Activations Density 0.008%

references to "pom" variations, which may relate to food or culinary contexts

No Comments

No Known Activations