INDEX

Explanations

references to a specific name or entity associated with "Ros."

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

eut

-0.16

ÑĪÐºÐ°

-0.15

resse

-0.15

iolet

-0.15

hoot

-0.14

autical

-0.14

wap

-0.14

POSITIVE LOGITS

ario

0.27

/ros

0.24

lyn

0.24

ARIO

0.23

coe

0.22

etta

0.22

ary

0.22

enthal

0.21

alia

0.21

arium

0.21

Activations Density 0.009%

references to a specific name or entity associated with "Ros."

No Comments

No Known Activations

references to a specific name or entity associated with "Ros."

No Comments

No Known Activations