INDEX

Explanations

instances of hesitation or uncertainty in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

hap

-0.16

luck

-0.15

YS

-0.14

fortunately

-0.14

ors

-0.14

alon

-0.14

ãĥ¼ãĥĦ

-0.14

ãĥ©ãĥĥãĤ¯

-0.14

versed

-0.13

xm

-0.13

POSITIVE LOGITS

man

0.38

boy

0.36

 holy

0.35

 lord

0.27

 trust

0.27

HOL

0.26

 Holy

0.26

boy

0.25

Boy

0.25

-boy

0.24

Activations Density 0.293%

instances of hesitation or uncertainty in a narrative

No Comments

No Known Activations