INDEX

Explanations

references to the publisher HarperCollins

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

spe

-0.17

ory

-0.17

ORY

-0.15

ãĤ¤ãĤ¹

-0.15

Ð¾ÑĢÑĥ

-0.15

orda

-0.15

isce

-0.14

Specifier

-0.14

AndUpdate

-0.14

POSITIVE LOGITS

Coll

0.22

 Collins

0.19

coll

0.18

íĺ¸

0.15

.qml

0.14

ç¯Ģ

0.14

Yar

0.14

atively

0.14

 ItemType

0.14

perimental

0.14

Activations Density 0.007%

references to the publisher HarperCollins

No Comments

No Known Activations