INDEX

Explanations

references to popular films, their directors, and associated awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 totiÅ¾

-0.16

 indeed

-0.16

thus

-0.16

 hence

-0.16

inde

-0.16

 thus

-0.15

à¤¦à¤°

-0.15

 Ð¸Ð¼ÐµÐ½Ð½Ð¾

-0.15

à¸Ńà¸°

-0.14

.getBoundingClientRect

-0.14

POSITIVE LOGITS

 likewise

0.49

 similarly

0.47

 ebenfalls

0.42

dit

0.39

dit

0.37

 equally

0.34

 Similarly

0.34

 Likewise

0.32

 meanwhile

0.32

 another

0.32

Activations Density 0.663%

references to popular films, their directors, and associated awards

No Comments

No Known Activations