INDEX

Explanations

references to customer support and service

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 personality

-0.17

 Personality

-0.17

-marker

-0.15

 pÅĤ

-0.15

ëĿ¼ë§Ī

-0.15

 marker

-0.15

itures

-0.14

OAD

-0.14

ificate

-0.13

.elem

-0.13

POSITIVE LOGITS

levator

0.15

olg

0.15

zw

0.15

,exports

0.14

åı£

0.14

ì²ĺ

0.14

ìĺ¨

0.14

 embargo

0.13

/customer

0.13

enne

0.13

Activations Density 0.033%

references to customer support and service

No Known Activations