INDEX

Explanations

technical jargon and abbreviations related to virtual reality and software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ideo

-0.20

olt

-0.18

/videos

-0.18

      ↵      ↵

-0.17

ect

-0.17

ideographic

-0.17

ector

-0.16

_voltage

-0.15

 valuable

-0.15

abit

-0.15

POSITIVE LOGITS

quez

0.23

atility

0.20

 versa

0.20

 dá»¥

0.20

OLUME

0.19

batim

0.19

ERTICAL

0.18

atile

0.18

ickers

0.17

islav

0.17

Activations Density 0.726%

technical jargon and abbreviations related to virtual reality and software

No Comments

No Known Activations