INDEX

Explanations

references to medical or biological terminology

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

arella

-0.16

à¸Ĺà¸²à¸ĩà¸ģà¸²à¸£

-0.16

@Web

-0.16

WI

-0.15

Wie

-0.15

ç´Ķ

-0.14

 OnTrigger

-0.14

-webpack

-0.14

elda

-0.14

leck

-0.14

POSITIVE LOGITS

0.17

 Chall

0.16

 targets

0.15

uala

0.15

DMI

0.15

chen

0.15

ori

0.14

 ãĤŃ

0.14

Hen

0.14

ãĥĺ

0.14

Activations Density 0.046%

references to medical or biological terminology

No Comments

No Known Activations