INDEX

Explanations

terms related to file processing and data extraction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ichte

-0.15

ÐµÐ»ÐµÐ½

-0.15

ARCH

-0.14

cab

-0.14

Ymd

-0.13

tÃŃ

-0.13

ypi

-0.13

ennen

-0.13

atisfied

-0.13

ono

-0.13

POSITIVE LOGITS

Elite

0.14

'gc

0.14

Gas

0.14

 elusive

0.14

 Duchess

0.13

ats

0.13

isch

0.13

umann

0.13

 Elite

0.13

èĹ

0.13

Activations Density 0.152%

terms related to file processing and data extraction

No Comments

No Known Activations