INDEX

Explanations

terms and characters from various Asian scripts

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

å®ĺ

-0.14

ereg

-0.14

ð

-0.14

Ð¾ÑģÐ½Ð¾Ð²

-0.13

ÃŃn

-0.13

Ù

-0.13

ÐµÐ³Ð¾ÑĢ

-0.13

azzi

-0.13

untu

-0.13

eyh

-0.13

POSITIVE LOGITS

jeta

0.16

å§«

0.14

 ìĿ´ìĸ´

0.14

TSR

0.13

ambre

0.13

illi

0.13

ynchronize

0.13

ubber

0.13

annel

0.13

Activations Density 0.023%

terms and characters from various Asian scripts

No Comments

No Known Activations