INDEX

Explanations

references to numbers and measurement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

umer

-0.19

ikt

-0.15

 cover

-0.15

kus

-0.15

ako

-0.15

Ø±Ø®

-0.14

IGIN

-0.14

ajs

-0.14

ëłĮ

-0.14

agon

-0.14

POSITIVE LOGITS

 respectively

0.21

 nhau

0.17

 ê°ģê°ģ

0.16

 respective

0.15

 each

0.15

åĲĦ

0.14

Geh

0.14

æ´ŀ

0.14

 themselves

0.13

teÅŁ

0.13

Activations Density 0.722%

references to numbers and measurement in various contexts

No Comments

No Known Activations