INDEX

Explanations

phrases that indicate checking for or assessing specific criteria or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Goodman

-0.17

éĶ¦

-0.16

 GOODMAN

-0.16

andom

-0.15

UNK

-0.15

imus

-0.15

stras

-0.15

oton

-0.14

odom

-0.14

igma

-0.14

POSITIVE LOGITS

 signs

0.28

 potential

0.23

 Signs

0.23

 whether

0.21

 possible

0.20

æĺ¯åĲ¦

0.19

 presence

0.19

gross

0.19

 Potential

0.18

 evidence

0.18

Activations Density 0.056%

phrases that indicate checking for or assessing specific criteria or conditions

No Comments

No Known Activations