INDEX

Explanations

content related to healthcare and social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-0.15

ãĢĭï¼Ī

-0.13

oot

-0.13

ange

-0.13

uck

-0.13

 Continued

-0.13

IBE

-0.13

aus

-0.13

 ãģĮ

-0.12

opy

-0.12

POSITIVE LOGITS

 There

0.19

 Although

0.19

 This

0.19

The

0.18

If

0.17

reetings

0.17

 When

0.17

 Since

0.16

 ************************************************************************

0.16

There

0.16

Activations Density 0.716%

content related to healthcare and social issues

No Comments

No Known Activations