INDEX

Explanations

terms related to significant changes or advancements in various contexts

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

etas

-0.16

umas

-0.16

sis

-0.16

zell

-0.15

dap

-0.15

ney

-0.14

æ²»

-0.14

ãģ¼

-0.14

rite

-0.14

CHAN

-0.14

POSITIVE LOGITS

ilde

0.18

 Fauc

0.17

nings

0.16

0.15

.sd

0.15

à¸¢à¸²à¸Ļ

0.15

ebin

0.14

avn

0.14

irim

0.14

Activations Density 0.278%

terms related to significant changes or advancements in various contexts

No Comments

No Known Activations