INDEX

Explanations

numbers indicating quantities or counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

etic

-0.15

 Davies

-0.14

åĮº

-0.13

ãĥ¼ãĥĸ

-0.13

 endregion

-0.13

arin

-0.13

mpr

-0.13

 Crystal

-0.13

olk

-0.13

ulary

-0.13

POSITIVE LOGITS

iese

0.23

 Swinger

0.17

leh

0.16

lett

0.16

 Gong

0.15

ISOString

0.15

ienie

0.15

RowAtIndexPath

0.14

[Index

0.14

 Polo

0.14

Activations Density 0.006%

numbers indicating quantities or counts

No Comments

No Known Activations