INDEX

Explanations

programming-related terms and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

asion

-0.17

ãĥ¼ãĥĢ

-0.16

 otherwise

-0.16

otherwise

-0.15

inker

-0.14

bins

-0.14

avo

-0.14

ellig

-0.14

Å¡tÃŃ

-0.14

oma

-0.14

POSITIVE LOGITS

 Ð¸Ð¼ÐµÐ½Ð½Ð¾

0.19

 only

0.18

çļĦæĺ¯

0.16

Ã¡y

0.15

shal

0.15

gesi

0.14

ITHER

0.14

à¹ģà¸Ħ

0.14

only

0.14

Activations Density 0.246%

programming-related terms and conditions

No Comments

No Known Activations