INDEX

Explanations

evaluative sentiments towards characters and their actions in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

/by

-0.16

AGO

-0.14

 Anyway

-0.14

actly

-0.14

è¨³

-0.14

sic

-0.13

å±Ĭ

-0.13

åº§

-0.13

Anyway

-0.13

 iÅŁte

-0.13

POSITIVE LOGITS

 granted

0.28

 maybe

0.26

 overall

0.24

 Overall

0.22

Granted

0.22

Overall

0.21

maybe

0.21

 personally

0.20

 Maybe

0.20

 sure

0.19

Activations Density 0.330%

evaluative sentiments towards characters and their actions in narratives

No Comments

No Known Activations