INDEX

Explanations

phrases and expressions directed at specific groups of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

rts

-0.15

oci

-0.14

irst

-0.14

_SPE

-0.14

utor

-0.14

äººäºº

-0.14

ftime

-0.14

ushima

-0.13

 safest

-0.13

nowledge

-0.13

POSITIVE LOGITS

 readers

0.26

 unfamiliar

0.23

 wondering

0.22

 Readers

0.21

 reader

0.21

 wonder

0.19

reader

0.19

-reader

0.18

 reading

0.18

Wonder

0.18

Activations Density 0.055%

phrases and expressions directed at specific groups of people

No Comments

No Known Activations