INDEX

Explanations

phrases that describe comparisons or contrasts between teams or projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

atore

-0.16

ÃŃÅ¡

-0.16

CKER

-0.15

alat

-0.15

_ros

-0.14

ten

-0.14

Ð»Ð¾Ð¶

-0.14

locator

-0.14

 ÑĢÐ¾Ð·

-0.13

omo

-0.13

POSITIVE LOGITS

 such

0.42

such

0.35

 SUCH

0.30

 like

0.27

 Such

0.26

Such

0.25

uch

0.24

 ÑĤÐ°ÐºÐ¸Ð¼Ð¸

0.23

 seperti

0.23

 ÑĤÐ°ÐºÐ¾Ð³Ð¾

0.23

Activations Density 0.156%

phrases that describe comparisons or contrasts between teams or projects

No Comments

No Known Activations