INDEX

Explanations

phrases indicating negative extreme scenarios or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

odd

-0.18

 opportunity

-0.17

antar

-0.17

 alphabet

-0.15

ees

-0.14

 opportunities

-0.14

zos

-0.14

Lod

-0.14

er

-0.14

POSITIVE LOGITS

-case

0.39

 Case

0.25

 case

0.25

case

0.23

Case

0.21

_case

0.21

 CASE

0.18

(case

0.18

	case

0.18

 offender

0.17

Activations Density 0.017%

phrases indicating negative extreme scenarios or outcomes

No Comments

No Known Activations