INDEX

Explanations

references to alumni and their achievements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

essim

-0.18

esser

-0.17

ding

-0.16

itti

-0.16

patrick

-0.15

kili

-0.15

assel

-0.15

ÑħÑĸÐ´

-0.15

allah

-0.14

grave

-0.14

POSITIVE LOGITS

panion

0.14

elerik

0.14

orna

0.14

Ð¾Ð²Ð°Ð½Ð¾

0.14

ceptor

0.14

Î¹Ïĩ

0.14

utor

0.14

è±Ĭ

0.13

rias

0.13

Wax

0.13

Activations Density 0.009%

references to alumni and their achievements

No Comments

No Known Activations