INDEX

Explanations

references to significant historical events or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

yte

-0.18

ÑĢÐµÐ¶

-0.18

/Internal

-0.17

esis

-0.17

avigator

-0.17

zell

-0.16

ofile

-0.16

Ã¢m

-0.16

egie

-0.15

.Serialization

-0.15

POSITIVE LOGITS

dr

0.15

cl

0.15

 Baron

0.15

 Chang

0.15

IDS

0.15

unch

0.15

0.14

.metamodel

0.14

Activations Density 0.241%

references to significant historical events or figures

No Comments

No Known Activations