INDEX

Explanations

references to dates and authorship within written content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 tant

-0.14

uku

-0.14

 Liberty

-0.14

iez

-0.14

 liberty

-0.13

erties

-0.13

yms

-0.13

ying

-0.13

-party

-0.13

 Corpor

-0.13

POSITIVE LOGITS

.HttpServlet

0.15

HAL

0.14

ÑĥÐ²Ð°

0.14

çĦ¶

0.13

omanip

0.13

 nomine

0.13

ndo

0.13

ÐºÐ¾ÑĤ

0.13

Ø±ÙĪÙĩ

0.13

TestFixture

0.13

Activations Density 0.055%

references to dates and authorship within written content

No Comments

No Known Activations