INDEX

Explanations

words related to chronic conditions or illnesses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

.FC

-0.15

Nim

-0.14

MLElement

-0.14

imitives

-0.13

cosystem

-0.13

anko

-0.13

 priv

-0.13

Pos

-0.13

.properties

-0.13

Ø±ÛĮÙĤ

-0.13

POSITIVE LOGITS

azzo

0.16

odyn

0.15

essler

0.15

 Dude

0.14

gio

0.14

mpar

0.14

gere

0.14

èĪį

0.14

arbon

0.13

arella

0.13

Activations Density 0.280%

words related to chronic conditions or illnesses

No Comments

No Known Activations