INDEX

Explanations

references and citations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iego

-0.18

umat

-0.16

ike

-0.16

owns

-0.14

andi

-0.14

.metro

-0.14

ams

-0.14

 Dear

-0.14

ole

-0.13

ongs

-0.13

POSITIVE LOGITS

ailles

0.16

celik

0.16

acyj

0.15

ysa

0.14

portun

0.14

æ¬ł

0.14

achsen

0.14

0.13

Activations Density 0.021%

references and citations in the text

No Comments

No Known Activations