INDEX

Explanations

references to trouble or problematic situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

nez

-0.18

merce

-0.18

ÅĻeba

-0.17

.scalablytyped

-0.17

.au

-0.16

pire

-0.15

ÐµÐ³Ð¾ÑĢ

-0.15

errer

-0.15

aras

-0.14

POSITIVE LOGITS

Trou

0.26

 Trou

0.25

 trouble

0.25

 Trouble

0.24

leshooting

0.17

 waters

0.17

 spots

0.17

/conf

0.17

©

0.17

ouble

0.17

Activations Density 0.025%

references to trouble or problematic situations

No Comments

No Known Activations