INDEX

Explanations

terms related to epidemiology and public health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ies

-0.17

 Buch

-0.15

lim

-0.15

na

-0.15

æºĸ

-0.14

.openapi

-0.14

mul

-0.14

|int

-0.14

-0.13

 seksi

-0.13

POSITIVE LOGITS

readcr

0.17

.utf

0.15

ynch

0.15

atti

0.15

_cast

0.15

ILT

0.14

éŃĶæ³ķ

0.14

yk

0.14

assi

0.14

rosso

0.14

Activations Density 0.001%

terms related to epidemiology and public health

No Comments

No Known Activations