INDEX

Explanations

punctuation marks and their associated contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

itters

-0.17

Î³ÎºÎ±

-0.16

avo

-0.16

hausen

-0.16

Ã¤ge

-0.15

arias

-0.14

ofire

-0.14

ocache

-0.14

iese

-0.13

ÐµÐ»ÐµÑĦÐ¾Ð½

-0.13

POSITIVE LOGITS

FAQ

0.20

 What

0.19

Overview

0.19

 conclusion

0.19

 overview

0.19

 FAQs

0.19

How

0.18

how

0.18

 Overview

0.18

 Types

0.18

Activations Density 0.087%

punctuation marks and their associated contexts

No Comments

No Known Activations