INDEX

Explanations

historical references to wars and military actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

aida

-0.16

Ð¾Ñĥ

-0.15

aira

-0.15

eft

-0.15

 serialVersionUID

-0.15

arsed

-0.15

ÑģÐµÐ½

-0.14

-Assad

-0.14

phia

-0.14

-LAST

-0.14

POSITIVE LOGITS

.scalablytyped

0.16

unde

0.16

 foot

0.15

VML

0.14

unnel

0.14

Ŀi

0.14

 McDon

0.14

åºĬ

0.14

 against

0.14

 Casc

0.14

Activations Density 0.510%

historical references to wars and military actions

No Comments

No Known Activations