INDEX

Explanations

phrases and prepositions indicating relationships and interactions between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é²ľ

-0.15

yro

-0.14

çĵľ

-0.14

anas

-0.13

.openConnection

-0.13

ERNEL

-0.13

ahkan

-0.13

vertising

-0.12

oks

-0.12

à¸ĸ

-0.12

POSITIVE LOGITS

 both

0.14

 Ã¢

0.13

çķ¥

0.13

 (!((

0.13

the

0.13

‘

0.13

 surrounding

0.13

 mart

0.13

 BOTH

0.13

Activations Density 1.459%

phrases and prepositions indicating relationships and interactions between concepts

No Comments

No Known Activations