INDEX

Explanations

numerical comparisons and salary figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 newText

-0.14

ÑĢÐ¾Ñģ

-0.14

iku

-0.14

antz

-0.14

acha

-0.14

áº½

-0.14

Ã³m

-0.14

Æ¯á»

-0.14

awi

-0.14

POSITIVE LOGITS

 similarly

0.19

irth

0.16

 comparable

0.15

ÐµÐ´Ð°Ðº

0.15

@index

0.15

 compart

0.14

.heroku

0.14

xCD

0.14

 Vend

0.14

<!--[

0.14

Activations Density 0.072%

numerical comparisons and salary figures

No Comments

No Known Activations