INDEX

Explanations

phrases related to medical or health-related warnings

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

orent

-0.15

 kraje

-0.14

 organ

-0.14

res

-0.14

elves

-0.14

 Messiah

-0.13

 Fork

-0.13

 ISSN

-0.13

leground

-0.13

ÑĥÐ´Ð°

-0.13

POSITIVE LOGITS

_mB

0.15

_mE

0.14

llu

0.14

_mD

0.14

uff

0.14

ondere

0.13

.cgi

0.13

cek

0.13

wg

0.13

erta

0.13

Activations Density 0.982%

phrases related to medical or health-related warnings

No Comments

No Known Activations