INDEX

Explanations

terms related to medical symptoms and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ady

-0.17

.Views

-0.16

 Mour

-0.16

ÛĮÚ©ÛĮ

-0.16

erie

-0.15

è¾¾

-0.15

undry

-0.15

³

-0.15

éĳ

-0.14

erty

-0.14

POSITIVE LOGITS

atology

0.27

atically

0.22

atik

0.19

 symptoms

0.17

/sign

0.17

ptoms

0.17

ally

0.17

lessly

0.16

onds

0.16

urm

0.15

Activations Density 0.012%

terms related to medical symptoms and their descriptions

No Comments

No Known Activations