INDEX

Explanations

suggestive phrases or indicators of actions and recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

olle

-0.18

igon

-0.17

 Vere

-0.16

ente

-0.15

iface

-0.15

ucz

-0.15

iper

-0.14

rient

-0.14

íĦ°

-0.14

POSITIVE LOGITS

indow

0.16

int

0.15

 enclosed

0.15

 Bundy

0.15

reed

0.14

xda

0.14

tas

0.14

contres

0.14

cliffe

0.14

inks

0.14

Activations Density 0.002%

suggestive phrases or indicators of actions and recommendations

No Comments

No Known Activations