INDEX

Explanations

dates and numerical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

éŀ

-0.17

okit

-0.16

 Hubb

-0.15

appa

-0.15

hub

-0.14

ollo

-0.14

iÄĩ

-0.14

azo

-0.14

orta

-0.14

umann

-0.14

POSITIVE LOGITS

feed

0.16

-feed

0.15

/DTD

0.14

Feed

0.14

stÃŃ

0.14

 feed

0.14

yonel

0.14

-haspopup

0.13

 DÃ¼n

0.13

ended

0.13

Activations Density 0.012%

dates and numerical references

No Comments

No Known Activations