INDEX

Explanations

connections and relationships between data, groups, and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

.gg

-0.15

áº¡

-0.15

.tech

-0.15

ÌĨ

-0.15

 -*-č↵

-0.15

uan

-0.14

 Äĩe

-0.13

afen

-0.13

ç¢°

-0.13

uc

-0.13

POSITIVE LOGITS

 suggests

0.51

 indication

0.49

 suggest

0.49

 indicates

0.48

 suggesting

0.48

suggest

0.48

 indicating

0.47

 indicate

0.47

 indications

0.42

 Indicates

0.42

Activations Density 0.293%

connections and relationships between data, groups, and events

No Comments

No Known Activations