INDEX

Explanations

financial and business performance indicators related to major companies

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

 addCriterion

-0.17

ayÄ±p

-0.16

 -*-č↵

-0.16

ichel

-0.16

Ð¾Ð±Ð°

-0.16

/Branch

-0.16

ÑħÐ¾Ð´Ð¸Ð¼

-0.15

 tolua

-0.15

WARDED

-0.15

 napÅĻ

-0.14

POSITIVE LOGITS

 reportedly

0.23

 till

0.20

 lately

0.19

 earlier

0.19

 allegedly

0.18

 said

0.18

 Reuters

0.17

 recently

0.17

 report

0.17

 according

0.17

Activations Density 0.110%

financial and business performance indicators related to major companies

No Comments

No Known Activations