INDEX

Explanations

phrases that signify exact locations or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 nearby

-0.17

endi

-0.15

adir

-0.15

 Nearby

-0.14

 nearer

-0.14

agento

-0.14

nearest

-0.14

ÃŃrk

-0.14

-0.13

Ø¨ÛĮÙĨ

-0.13

POSITIVE LOGITS

 outside

0.21

 below

0.17

outside

0.17

 feet

0.16

cta

0.16

 weeks

0.16

 moments

0.15

 before

0.15

 days

0.15

 interior

0.15

Activations Density 0.042%

phrases that signify exact locations or measurements

No Comments

No Known Activations

phrases that signify exact locations or measurements

No Comments

No Known Activations