INDEX

Explanations

instances of the word "from," indicating a focus on source or origin references in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

zac

-0.17

å®Ļ

-0.15

*size

-0.15

PullParser

-0.14

antage

-0.14

oko

-0.13

habi

-0.13

 '/',↵

-0.13

 Bloc

-0.13

áº¥p

-0.13

POSITIVE LOGITS

"./

0.23

'./

0.21

 "../

0.19

 '../

0.17

./

0.16

../

0.16

"@

0.16

'@

0.16

á»©ng

0.15

 common

0.15

Activations Density 0.004%

instances of the word "from," indicating a focus on source or origin references in the text

No Comments

No Known Activations