INDEX

Explanations

references to questions and discussions about controversial topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adem

-0.17

arry

-0.16

ãģķãĤī

-0.15

åĶ¯

-0.15

OutOf

-0.15

 USHORT

-0.14

ONSE

-0.14

ickey

-0.14

oman

-0.14

.getElements

-0.14

POSITIVE LOGITS

mmo

0.15

.Generated

0.15

izont

0.14

nels

0.14

.baidu

0.14

illery

0.14

esian

0.14

CST

0.14

ksen

0.14

icos

0.14

Activations Density 0.129%

references to questions and discussions about controversial topics

No Comments

No Known Activations