INDEX

Explanations

phrases related to business operations and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otel

-0.15

zin

-0.14

olume

-0.14

 kÃ©m

-0.14

 Barton

-0.14

hop

-0.13

must

-0.13

orse

-0.13

iven

-0.13

å¸ĮæľĽ

-0.13

POSITIVE LOGITS

 properly

0.23

proper

0.21

 stays

0.20

 proper

0.19

 understood

0.18

 Proper

0.18

æŃ£ç¡®

0.17

 Ð¿ÑĢÐ°Ð²Ð¸Ð»ÑĮÐ½Ð¾

0.17

 olab

0.17

 correctly

0.16

Activations Density 0.150%

phrases related to business operations and responsibilities

No Comments

No Known Activations