INDEX

Explanations

variations of the word "or"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

/or

-0.15

edBy

-0.15

itÃ©s

-0.14

AMP

-0.14

essen

-0.14

arella

-0.14

nore

-0.14

ushman

-0.14

rogen

-0.14

dar

-0.14

POSITIVE LOGITS

chest

0.19

Tar

0.17

Tar

0.17

iente

0.15

agan

0.15

odox

0.15

 maybe

0.15

dn

0.15

maybe

0.14

ooter

0.14

Activations Density 0.049%

variations of the word "or"

No Comments

No Known Activations