INDEX

Explanations

specific time-related measures and comparisons in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

gis

-0.16

ickets

-0.15

Å¾ÃŃ

-0.14

uly

-0.14

 unborn

-0.14

 Knot

-0.14

xo

-0.14

gig

-0.14

Î¯Î´Î±

-0.13

iesta

-0.13

POSITIVE LOGITS

 follow

0.32

 Follow

0.24

follow

0.24

 study

0.23

 Visit

0.23

Follow

0.22

 visit

0.21

 baseline

0.21

-follow

0.20

study

0.19

Activations Density 0.048%

specific time-related measures and comparisons in data

No Comments

No Known Activations