INDEX

Explanations

specific details related to medical or scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

smith

-0.14

hait

-0.14

pell

-0.14

Ã£n

-0.13

mate

-0.13

atomy

-0.13

 Tops

-0.13

weather

-0.13

loc

-0.13

ains

-0.13

POSITIVE LOGITS

lluminate

0.14

cio

0.14

ItemImage

0.14

.fig

0.14

-uppercase

0.14

çĴ°

0.14

ÐµÐ³Ð¾Ð´Ð½Ñı

0.13

istrovstvÃŃ

0.13

akra

0.13

eum

0.13

Activations Density 1.807%

specific details related to medical or scientific concepts

No Comments

No Known Activations