INDEX

Explanations

occurrences of the preposition "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

anoia

-0.15

/Area

-0.15

Ð»ÐµÐ¼

-0.15

ÐµÑģÐ°

-0.15

imens

-0.14

Ðµ

-0.14

dfa

-0.14

erli

-0.14

MainFrame

-0.14

omen

-0.14

POSITIVE LOGITS

enet

0.16

opis

0.15

cales

0.14

\Doctrine

0.14

rio

0.14

TexParameter

0.14

 ÑģÑĤÐµÐº

0.14

XML

0.14

retched

0.13

Î»Î¹Î¬

0.13

Activations Density 0.045%

occurrences of the preposition "in."

No Comments

No Known Activations