INDEX

Explanations

specific instances of various activities, events, and initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 various

-0.19

etc

-0.19

 everywhere

-0.18

 stuff

-0.18

 Various

-0.18

all

-0.17

åĲĦç§į

-0.17

æīĢæľī

-0.16

Various

-0.15

 throughout

-0.15

POSITIVE LOGITS

åĪĨåĪ«

0.28

ãĢģä¸Ģ

0.21

—one

0.20

 respectively

0.20

-two

0.20

-one

0.20

ãģĿãĤĮ

0.19

 ê°ģê°ģ

0.18

atat

0.18

Ø¹Ø§ÙĨ

0.18

Activations Density 0.280%

specific instances of various activities, events, and initiatives

No Comments

No Known Activations