INDEX

Explanations

references to events and their coverage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

VERTISEMENT

-0.18

 ç¤º

-0.17

 fucks

-0.15

avicon

-0.15

annes

-0.15

ìĤ´

-0.14

kop

-0.14

alim

-0.14

jÃŃ

-0.14

VERTISE

-0.14

POSITIVE LOGITS

 report

0.31

 reports

0.26

 reporting

0.25

 coverage

0.25

 photos

0.25

 reported

0.24

 impressions

0.23

photos

0.23

report

0.23

.report

0.22

Activations Density 0.172%

references to events and their coverage

No Comments

No Known Activations