INDEX

Explanations

punctuation marks within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

umi

-0.15

_MACRO

-0.14

ayd

-0.13

çĦ¦

-0.13

obel

-0.13

 WaitForSeconds

-0.13

ucus

-0.13

 intelligent

-0.13

STANCE

-0.13

arl

-0.13

POSITIVE LOGITS

nant

0.15

Î¾Î¹

0.15

.RightToLeft

0.15

Ð½Ð°Ðº

0.14

owie

0.14

enko

0.14

ĪæĿĥ

0.14

itty

0.14

aber

0.13

 braz

0.13

Activations Density 0.016%

punctuation marks within the text

No Comments

No Known Activations