INDEX

Explanations

forms of the verb "to be."

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

endet

-0.17

AGO

-0.16

à¸Ńà¸°

-0.15

idad

-0.14

aber

-0.14

ucus

-0.14

jumbotron

-0.14

allback

-0.13

 necessary

-0.13

 justification

-0.13

POSITIVE LOGITS

 unclear

0.20

 clear

0.19

zac

0.17

 unlikely

0.17

 premature

0.17

likely

0.16

 likely

0.16

SSIP

0.16

 likelihood

0.16

meleri

0.15

Activations Density 0.072%

forms of the verb "to be."

No Comments

No Known Activations