INDEX

Explanations

references to customer service and related interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uste

-0.19

ippi

-0.18

oul

-0.18

sy

-0.17

sv

-0.16

ê¹

-0.16

ishments

-0.16

rimp

-0.15

_cust

-0.15

yan

-0.15

POSITIVE LOGITS

/client

0.25

Ã¨le

0.22

ç«¯

0.20

ç»ıçĲĨ

0.18

-server

0.17

ikan

0.17

-service

0.17

ele

0.16

care

0.16

 sáº¡n

0.16

Activations Density 0.023%

references to customer service and related interactions

No Comments

No Known Activations