INDEX

Explanations

phrases indicating the presence of citations or references to previous works and excerpts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.14

ropped

-0.14

lette

-0.14

ç·Ĵ

-0.14

ÐµÑĤÐ°

-0.14

ass

-0.14

/details

-0.13

mal

-0.13

ìĨĮ

-0.13

POSITIVE LOGITS

 originally

0.18

ogui

0.17

 original

0.16

storybook

0.16

 Ð¾ÑĢÐ¸Ð³

0.15

.original

0.15

 pÅ¯vod

0.15

etooth

0.15

 Originally

0.15

_pci

0.15

Activations Density 0.084%

phrases indicating the presence of citations or references to previous works and excerpts

No Comments

No Known Activations