INDEX

Explanations

phrases related to proven success or reliability in performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

lingen

-0.15

ÑħÑĸÐ´

-0.14

robe

-0.14

 Misc

-0.14

Mag

-0.14

aravel

-0.14

erli

-0.14

sterol

-0.13

ude

-0.13

POSITIVE LOGITS

 orth

0.15

istrovstvÃŃ

0.15

ä»ĺãģį

0.14

ska

0.14

aight

0.14

eyen

0.14

rvÃ©

0.14

.hwp

0.14

ALER

0.14

TEGER

0.14

Activations Density 0.009%

phrases related to proven success or reliability in performance

No Comments

No Known Activations