INDEX

Explanations

financial metrics and statistics related to occupations and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

.nih

-0.17

:///

-0.16

LOY

-0.15

Î¼Î¯

-0.15

ledon

-0.14

overy

-0.14

ropolitan

-0.14

.cgi

-0.14

eyond

-0.14

ablish

-0.14

POSITIVE LOGITS

/Product

0.16

/Instruction

0.16

rud

0.16

/Application

0.16

0.15

/Branch

0.15

-Free

0.15

/Sub

0.15

/Area

0.15

/P

0.14

Activations Density 0.161%

financial metrics and statistics related to occupations and media

No Comments

No Known Activations