INDEX

Explanations

abbreviations and initials typically associated with names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

å·¦åı³

-0.16

esan

-0.16

aly

-0.15

tit

-0.14

onth

-0.14

 Lesser

-0.14

valu

-0.13

achat

-0.13

à¥Īà¤ķ

-0.13

POSITIVE LOGITS

utta

0.17

ulus

0.16

odian

0.16

æŁĵ

0.15

ABEL

0.15

ÙĦÙĪ

0.14

 ãĥ¯

0.14

Ã¼k

0.14

uta

0.14

 seriousness

0.14

Activations Density 0.040%

abbreviations and initials typically associated with names

No Comments

No Known Activations