INDEX

Explanations

details related to specific events and individuals involved in those events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

åŃĺäºİ

-0.15

owler

-0.15

rchive

-0.14

phans

-0.14

 Kapoor

-0.14

LEGRO

-0.14

yer

-0.14

Î¬Î»Î¹

-0.14

heimer

-0.14

POSITIVE LOGITS

è¢

0.18

osc

0.16

 wore

0.15

untas

0.14

erval

0.14

 porta

0.14

Yol

0.13

ÑİÐº

0.13

 Landing

0.13

.scalablytyped

0.13

Activations Density 0.548%

details related to specific events and individuals involved in those events

No Comments

No Known Activations