INDEX

Explanations

elements related to product specifications and features

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

Ã©tÃ©

-0.19

 tarif

-0.17

 Hava

-0.15

.nasa

-0.15

resar

-0.15

ichi

-0.14

elta

-0.14

Ð²Ð¾Ð·

-0.14

licted

-0.14

POSITIVE LOGITS

 ensures

0.22

 ensure

0.22

 means

0.22

 mean

0.19

 ensuring

0.19

 Means

0.18

 make

0.18

olis

0.17

 allows

0.17

 further

0.17

Activations Density 0.127%

elements related to product specifications and features

No Comments

No Known Activations