INDEX

Explanations

phrases that involve numerical and time-based references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

à¸¥à¸°

-0.15

ardin

-0.15

antt

-0.14

bjerg

-0.14

aurus

-0.14

iswa

-0.14

ovie

-0.14

æ³ī

-0.13

£

-0.13

aler

-0.13

POSITIVE LOGITS

>Lorem

0.16

oleÄį

0.14

 ëķ

0.14

 today

0.14

erves

0.14

ield

0.14

åĴ²

0.14

 unordered

0.13

nik

0.13

Activations Density 0.083%

phrases that involve numerical and time-based references

No Comments

No Known Activations