INDEX

Explanations

references to company names and corporate entities in the context of announcements or news

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.19

-0.18

 convention

-0.17

zel

-0.15

pos

-0.15

 tech

-0.15

 posit

-0.14

ZA

-0.14

 prost

-0.14

 techn

-0.14

POSITIVE LOGITS

(åľŁ

0.16

ekce

0.15

 fres

0.15

à¸ªà¸°

0.15

dings

0.15

ensch

0.15

 Fleming

0.15

AtPath

0.14

 kÃ¼t

0.14

edii

0.14

Activations Density 0.006%

references to company names and corporate entities in the context of announcements or news

No Comments

No Known Activations