INDEX

Explanations

terms related to pharmaceuticals and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Ð¸Ð´

-0.17

Ik

-0.17

IK

-0.16

ik

-0.16

ibaba

-0.16

 ICON

-0.16

.GeneratedValue

-0.15

 heiÃŁ

-0.15

(home

-0.15

 Howell

-0.15

POSITIVE LOGITS

 Keep

0.17

Keep

0.16

 Keeps

0.16

 Just

0.16

 Judgment

0.16

 Keeping

0.15

 judgment

0.15

 Knowing

0.15

 Judge

0.15

Keys

0.15

Activations Density 0.031%

terms related to pharmaceuticals and medical conditions

No Comments

No Known Activations