INDEX

Explanations

specific entities or terminologies related to scientific or technical contexts

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

.myapplication

-0.15

endar

-0.15

attles

-0.14

alara

-0.14

<dd

-0.14

annes

-0.14

uctor

-0.13

.bd

-0.13

ismet

-0.13

HostName

-0.13

POSITIVE LOGITS

 Platt

0.15

zell

0.15

 blues

0.15

erse

0.14

LZ

0.14

 ÐĿÐ°Ñģ

0.14

wat

0.14

Chooser

0.13

adow

0.13

azor

0.13

Activations Density 0.867%

specific entities or terminologies related to scientific or technical contexts

No Comments

No Known Activations