INDEX

Explanations

terms specifically related to technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Technologies

-0.23

 technology

-0.18

 technologies

-0.17

/Branch

-0.17

 Technology

-0.17

 tecn

-0.16

Technology

-0.16

mente

-0.15

otechn

-0.15

 TECHNO

-0.15

POSITIVE LOGITS

ies

0.32

0.21

sav

0.21

ÂŃn

0.21

stars

0.21

quila

0.20

iques

0.20

IES

0.20

ical

0.19

onomy

0.19

Activations Density 0.013%

terms specifically related to technology

No Comments

No Known Activations