INDEX

Explanations

phrases that indicate time or specific points of reference in a timeline

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 ÑĥÑģÐ»

-0.17

ÑĢÐ¾Ñĩ

-0.16

usch

-0.16

zsche

-0.15

Ð¸Ð½Ð¾Ð²

-0.15

Convention

-0.15

issen

-0.14

isÃ©

-0.14

zag

-0.14

quis

-0.14

POSITIVE LOGITS

 discretion

0.16

mani

0.16

tt

0.15

ault

0.14

 nackte

0.13

Fur

0.13

ftime

0.13

encing

0.13

Activations Density 0.076%

phrases that indicate time or specific points of reference in a timeline

No Comments

No Known Activations