INDEX

Explanations

medical terms related to diseases and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

enza

-0.17

ump

-0.15

edition

-0.14

orgen

-0.14

ongan

-0.14

èªĮ

-0.14

Knight

-0.14

erland

-0.13

logan

-0.13

å±Ĭ

-0.13

POSITIVE LOGITS

ersh

0.17

egasus

0.17

ias

0.17

roj

0.16

Ú¯Ø±Ø§ÙĨ

0.15

Ã©ric

0.15

allo

0.14

bett

0.13

anium

0.13

&a

0.13

Activations Density 0.027%

medical terms related to diseases and conditions

No Comments

No Known Activations