INDEX

Explanations

information concerning health and medical topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 then

-0.28

 Then

-0.26

then

-0.25

 THEN

-0.24

Then

-0.21

THEN

-0.21

 entÃ£o

-0.19

poi

-0.18

 puis

-0.18

 dann

-0.17

POSITIVE LOGITS

ÑĢÐ°Ð

0.20

Ð°Ð

0.19

Ð¾Ð

0.19

urrenc

0.17

wom

0.17

leyin

0.17

 Europ

0.17

eyJ

0.17

IIIK

0.16

gend

0.16

Activations Density 0.339%

information concerning health and medical topics

No Comments

No Known Activations