INDEX

Explanations

mathematical or computational relationships and values

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

iento

-0.15

avings

-0.15

ym

-0.14

ceptions

-0.14

.inline

-0.14

elsey

-0.14

-0.13

ritis

-0.13

iana

-0.13

ÑĥÑĩ

-0.13

POSITIVE LOGITS

ipt

0.16

Ð»Ð°Ð·

0.15

ezi

0.15

eyJ

0.14

 è¶

0.14

ICAST

0.14

ez

0.14

èĺ

0.14

eya

0.14

.UnitTesting

0.14

Activations Density 0.115%

mathematical or computational relationships and values

No Comments

No Known Activations