INDEX

Explanations

terms related to news updates and announcements regarding events or opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ãģĹãģĭ

-0.14

imli

-0.13

eton

-0.13

 æ¶

-0.13

chod

-0.13

 Rewards

-0.13

_YUV

-0.13

ffer

-0.13

_aux

-0.13

[++

-0.13

POSITIVE LOGITS

 courtesy

0.90

 thanks

0.89

thanks

0.76

 Thanks

0.69

Thanks

0.67

 Courtesy

0.67

cour

0.65

Courtesy

0.57

 gracias

0.57

 nhá»Ŀ

0.49

Activations Density 0.338%

terms related to news updates and announcements regarding events or opportunities

No Comments

No Known Activations