INDEX

Explanations

references to specific companies and financial metrics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

isl

-0.17

aggio

-0.15

ay

-0.15

unl

-0.15

elpers

-0.14

assin

-0.14

acific

-0.14

 æ¢

-0.14

iffe

-0.14

"display

-0.14

POSITIVE LOGITS

iquÃ©

0.15

oop

0.14

-rating

0.13

ASM

0.13

ITOR

0.13

 Banc

0.13

asma

0.13

Wildcard

0.13

HandlerContext

0.13

 example

0.13

Activations Density 0.318%

references to specific companies and financial metrics

No Comments

No Known Activations