INDEX

Explanations

acronyms and designations related to organizations and associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

akin

-0.16

ment

-0.15

 ment

-0.15

yth

-0.15

achuset

-0.15

atu

-0.14

ardo

-0.14

inos

-0.14

ÙĦÙħØ§ÙĨ

-0.14

issen

-0.13

POSITIVE LOGITS

stra

0.18

ron

0.17

 Meetings

0.16

sled

0.15

HCI

0.15

lum

0.15

eyer

0.15

 porr

0.14

)>>

0.14

Äĥn

0.14

Activations Density 0.014%

acronyms and designations related to organizations and associations

No Comments

No Known Activations