INDEX

Explanations

phrases related to medical case studies and epidemiological findings

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

.scalablytyped

-0.19

$MESS

-0.17

undy

-0.17

ansi

-0.16

rok

-0.16

olare

-0.15

á¿Ĩ

-0.14

ÏĢÎ·

-0.14

ï»¿#

-0.14

.splitext

-0.14

POSITIVE LOGITS

0.18

bolt

0.16

 dock

0.16

 bolt

0.15

on

0.15

ses

0.15

 case

0.14

Activations Density 0.040%

phrases related to medical case studies and epidemiological findings

No Comments

No Known Activations