INDEX

Explanations

references to financial analysts and their ratings or predictions regarding stock performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

åħ¼

-0.18

cular

-0.16

erve

-0.16

ulary

-0.15

Ø§ÙħØª

-0.15

-hooks

-0.15

åĢį

-0.15

hooks

-0.15

ocket

-0.14

mere

-0.14

POSITIVE LOGITS

cup

0.15

å¯¿

0.14

æĿ¯

0.14

ÄĽn

0.14

 voices

0.14

log

0.13

Ã©gor

0.13

 ä¸ĸ

0.13

 span

0.13

Ã¶t

0.12

Activations Density 0.013%

references to financial analysts and their ratings or predictions regarding stock performance

No Comments

No Known Activations