INDEX

Explanations

terms related to corporate branding and mergers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

COD

-0.16

ãĤ¹ãĥĨãĤ£

-0.15

.esp

-0.15

ÌĨ

-0.15

zar

-0.15

Ã¢l

-0.14

ç´¯

-0.14

pdo

-0.14

orth

-0.14

.nasa

-0.14

POSITIVE LOGITS

 Ernst

0.29

Del

0.26

 audit

0.22

EY

0.22

tax

0.21

 auditing

0.20

Tax

0.19

 Audit

0.19

Del

0.19

 Consulting

0.19

Activations Density 0.026%

terms related to corporate branding and mergers

No Comments

No Known Activations