INDEX

Explanations

phrases expressing limitations or negations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

arse

-0.15

Ã¶h

-0.14

aka

-0.14

iez

-0.14

-utils

-0.13

TS

-0.13

 ìŀĪëĭ¤ëĬĶ

-0.13

pom

-0.13

gaard

-0.13

aits

-0.13

POSITIVE LOGITS

 question

0.29

 denying

0.28

way

0.26

 doubt

0.26

 point

0.26

 reason

0.26

 disput

0.26

 deny

0.21

 need

0.21

question

0.20

Activations Density 0.043%

phrases expressing limitations or negations

No Comments

No Known Activations