INDEX

Explanations

words related to rewards and deals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eyse

-0.17

vana

-0.15

 Staples

-0.15

ORK

-0.14

Writable

-0.14

Ø¶Ùħ

-0.14

UMB

-0.14

ModelState

-0.14

pras

-0.13

Shock

-0.13

POSITIVE LOGITS

0.15

 trick

0.14

ç¹Ķ

0.14

]âĢı

0.14

ilver

0.13

ìļ´

0.13

bet

0.13

Ð½Ð¾Ð¿

0.13

iyon

0.13

 kÃ¥

0.13

Activations Density 0.001%

words related to rewards and deals

No Comments

No Known Activations