INDEX

Explanations

quantifiers and numerical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

stuff

-0.16

 endeavor

-0.15

iam

-0.14

jam

-0.14

.Areas

-0.14

 legis

-0.13

oub

-0.13

erm

-0.13

 parcel

-0.13

 phÃ¢n

-0.13

POSITIVE LOGITS

 times

0.21

 tries

0.17

 people

0.16

 beers

0.16

 hours

0.15

 martin

0.15

 trips

0.15

 minutes

0.15

gaz

0.15

 chances

0.15

Activations Density 0.220%

quantifiers and numerical expressions

No Comments

No Known Activations