INDEX

Explanations

phrases suggesting enthusiasm or appreciation

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

usi

-0.15

uxe

-0.14

æĹıèĩªæ²»

-0.14

 Pillow

-0.14

draul

-0.14

 thumb

-0.14

Ð»ÑİÐ±

-0.13

Ð¾ÑĤÑĮ

-0.13

gressor

-0.13

ancode

-0.13

POSITIVE LOGITS

%č↵

0.14

HAM

0.13

dÃ¼ÄŁ

0.13

addtogroup

0.13

dÃ¼k

0.13

ãĤ¿ãĥ«

0.13

 Î¥ÏĢÎ¿

0.12

ujte

0.12

ORY

0.12

UGIN

0.12

Activations Density 1.936%

phrases suggesting enthusiasm or appreciation

No Comments

No Known Activations