INDEX

Explanations

terms related to presentations and PowerPoint content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

abyrinth

-0.15

wit

-0.15

olas

-0.14

_pad

-0.14

bane

-0.14

verte

-0.14

shan

-0.14

null

-0.14

ÑģÐ¿

-0.14

 already

-0.14

POSITIVE LOGITS

anut

0.18

idual

0.18

roj

0.17

WithDuration

0.15

jiang

0.15

usu

0.15

yne

0.15

avery

0.15

erno

0.14

Ð¶Ð´

0.14

Activations Density 0.017%

terms related to presentations and PowerPoint content

No Comments

No Known Activations