INDEX

Explanations

events and changes related to significant incidents and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ulis

-0.16

RIES

-0.15

Ð¸Ð½Ð¸

-0.15

ogs

-0.14

isor

-0.14

ÑĢÐ°Ð½Ð¸ÑĨ

-0.14

atak

-0.14

-0.13

Fog

-0.13

ichert

-0.13

POSITIVE LOGITS

 when

0.33

when

0.27

 cuando

0.25

 Ø¹ÙĨØ¯ÙħØ§

0.24

 quando

0.24

 When

0.23

 lorsque

0.23

 WHEN

0.22

_when

0.21

When

0.21

Activations Density 0.189%

events and changes related to significant incidents and their consequences

No Comments

No Known Activations