INDEX

Explanations

terms related to health conditions and medical concepts, especially those associated with hepatitis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

op

-0.15

ika

-0.14

zap

-0.14

azar

-0.14

çıŃ

-0.14

older

-0.14

zap

-0.14

Äļ

-0.13

_continue

-0.13

rag

-0.13

POSITIVE LOGITS

lett

0.35

itt

0.25

ITT

0.20

ett

0.18

lette

0.17

son

0.17

ittal

0.17

Ð»ÐµÑĤ

0.16

ritt

0.16

FY

0.15

Activations Density 0.007%

terms related to health conditions and medical concepts, especially those associated with hepatitis

No Comments

No Known Activations