INDEX

Explanations

phrases and structures that indicate relationships or connections between entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

onso

-0.17

 bibliography

-0.14

ilm

-0.14

 otherwise

-0.14

 Song

-0.14

 more

-0.14

.getInstance

-0.14

ibli

-0.14

 SWITCH

-0.14

POSITIVE LOGITS

endir

0.16

.unwrap

0.15

emean

0.15

endor

0.15

Muon

0.15

ÐµÐ½Ñģ

0.15

ÐŁÐļ

0.15

irie

0.15

ENDOR

0.14

zia

0.14

Activations Density 0.439%

phrases and structures that indicate relationships or connections between entities

No Comments

No Known Activations