INDEX

Explanations

locations and organizational structures or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

arten

-0.20

gaard

-0.16

 replace

-0.16

onte

-0.16

eras

-0.15

Ãºa

-0.15

atk

-0.14

Ø±Ø³

-0.14

.replace

-0.14

POSITIVE LOGITS

 finally

0.28

finally

0.25

 Finally

0.20

Finally

0.20

och

0.19

 previously

0.18

ç»Īäºİ

0.17

	finally

0.16

Previously

0.16

redient

0.16

Activations Density 0.005%

locations and organizational structures or systems

No Comments

No Known Activations