INDEX

Explanations

phrases indicating collaboration and teamwork

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

 revis

-0.18

nemonic

-0.17

 brib

-0.15

 ampl

-0.15

ç¤

-0.15

 amplify

-0.15

 starring

-0.14

 travers

-0.14

 annot

-0.14

 dealloc

-0.14

POSITIVE LOGITS

be

0.26

get

0.25

 conduct

0.23

 become

0.23

 make

0.22

 start

0.21

 take

0.20

add

0.20

 perform

0.19

 give

0.19

Activations Density 1.079%

phrases indicating collaboration and teamwork

No Comments

No Known Activations