INDEX

Explanations

structured data-related patterns or formats, possibly indicating time stamps or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

or

-0.15

kola

-0.14

ol

-0.14

 Gross

-0.13

Ð¾ÑĢÑıÐ´

-0.13

ãĥ³ãĥĦ

-0.13

ä¼Ŀ

-0.13

 hunted

-0.13

Ã¼r

-0.13

 hunters

-0.13

POSITIVE LOGITS

.bootstrapcdn

0.14

íı¬

0.14

ÏĥÏĦÎ¿

0.14

ftime

0.14

-Za

0.14

idata

0.14

/english

0.14

ViewById

0.13

DebugEnabled

0.13

Activations Density 0.056%

structured data-related patterns or formats, possibly indicating time stamps or identifiers

No Comments

No Known Activations