INDEX

Explanations

numerical data and specific references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

iyim

-0.17

urette

-0.16

.cgi

-0.15

ESCO

-0.14

sted

-0.14

ãģ®ãģłãĤįãģĨ

-0.14

PCA

-0.14

jos

-0.14

jang

-0.14

faq

-0.14

POSITIVE LOGITS

ument

0.17

utan

0.16

eri

0.15

eyh

0.15

ern

0.14

 Indians

0.14

omba

0.14

 /**<

0.13

oni

0.13

uyu

0.13

Activations Density 0.186%

numerical data and specific references

No Comments

No Known Activations