INDEX

Explanations

words related to exhibitions and exhibits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ffect

-0.20

kits

-0.17

htub

-0.17

 prod

-0.15

excel

-0.15

XL

-0.14

åĦĢ

-0.14

ffects

-0.14

headed

-0.14

ëģĶ

-0.14

POSITIVE LOGITS

/import

0.20

Ú¯Ø§Ùĩ

0.17

è§Ī

0.17

æŁľ

0.16

ose

0.16

ize

0.16

ism

0.15

è¦§

0.15

ãĥ³ãĥĲ

0.15

Activations Density 0.014%

words related to exhibitions and exhibits

No Comments

No Known Activations