INDEX

Explanations

terms related to book publication and literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

åª

-0.16

ãĤ·ãĤ¢

-0.15

ossa

-0.15

usercontent

-0.14

Verdana

-0.14

abay

-0.14

ignon

-0.13

ÑıÐ±

-0.13

ono

-0.13

 Pear

-0.13

POSITIVE LOGITS

--

0.20

--

0.19

"@

0.18

--[

0.17

"@

0.17

âĪ¨

0.16

âĢį

0.16

0.15

âĢı

0.15

)--

0.15

Activations Density 0.019%

terms related to book publication and literary works

No Comments

No Known Activations