INDEX

Explanations

components related to reviews and recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

å¾ģ

-0.15

/rc

-0.14

porate

-0.14

 armored

-0.13

.fn

-0.13

Ã©st

-0.13

rani

-0.13

=yes

-0.13

 invis

-0.13

POSITIVE LOGITS

ÑĤÐ¾ÑĦ

0.17

AIT

0.16

strup

0.15

aft

0.15

à¸Ķà¸²

0.14

.newLine

0.14

ungan

0.14

ãĤ¶ãĥ¼

0.14

 éģĵ

0.13

itchen

0.13

Activations Density 0.005%

components related to reviews and recommendations

No Comments

No Known Activations