INDEX

Explanations

references to specific months, particularly focusing on March and the month of August

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

headed

-0.16

 Weekly

-0.16

akin

-0.15

ist

-0.15

zelf

-0.14

hr

-0.14

artin

-0.14

ccount

-0.14

ition

-0.14

kinson

-0.14

POSITIVE LOGITS

ä»½

0.35

-long

0.35

/year

0.34

long

0.27

lies

0.26

/month

0.25

-old

0.23

-end

0.20

iversary

0.20

éĸĵ

0.18

Activations Density 0.050%

references to specific months, particularly focusing on March and the month of August

No Comments

No Known Activations