INDEX

Explanations

HTML tags and elements within a document

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

voke

-0.16

ulan

-0.15

 Passenger

-0.14

Ð¿Ð¾Ð½

-0.14

oa

-0.14

Ã¼cken

-0.14

ooting

-0.14

uire

-0.14

finger

-0.13

iÄį

-0.13

POSITIVE LOGITS

æ²ĸ

0.15

.AutoScaleMode

0.15

ë¦¬ìķĦ

0.15

rov

0.14

/LICENSE

0.14

 ÐºÐ¾Ð»ÑĮ

0.14

},'

0.13

rw

0.13

olen

0.13

 Ð³Ð¾Ð»Ð¾Ð²Ñĥ

0.13

Activations Density 0.004%

HTML tags and elements within a document

No Known Activations