INDEX

Explanations

instances of uncertainty or doubt in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

SOS

-0.15

zeug

-0.14

èķ

-0.14

SOP

-0.14

bin

-0.14

rey

-0.13

Pry

-0.13

izmet

-0.13

 Burnett

-0.13

 block

-0.13

POSITIVE LOGITS

ighted

0.18

 sounding

0.18

 SOUND

0.18

Sounds

0.16

Ã±ana

0.15

/Runtime

0.15

:animated

0.15

achs

0.15

 Ð¾ÑĩÐµÑĢÐµÐ´

0.14

 sounds

0.14

Activations Density 0.061%

instances of uncertainty or doubt in statements

No Comments

No Known Activations