INDEX

Explanations

symbols and formatting indicators related to financial data

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

icont

-0.17

-0.16

á»©ng

-0.16

llen

-0.16

ones

-0.15

 Boeh

-0.15

ic

-0.14

enza

-0.14

POSITIVE LOGITS

antee

0.16

ialis

0.16

 /*#__

0.15

abil

0.14

 Hercules

0.14

 vÃłng

0.14

onn

0.14

leneck

0.14

izr

0.13

oogle

0.13

Activations Density 0.003%

symbols and formatting indicators related to financial data

No Comments

No Known Activations