INDEX

Explanations

references to legal and governmental frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Beam

-0.17

.scalablytyped

-0.14

 Beam

-0.14

Beat

-0.14

ÏĢÎ®

-0.14

âĢĮÚ©ÙĨ

-0.14

umba

-0.14

 Beat

-0.13

reachable

-0.13

ÏĥÎ¹ÎµÏį

-0.13

POSITIVE LOGITS

be

1.05

be

0.57

Be

0.56

Be

0.47

 Ø¨Ø§Ø´Ø¯

0.46

be

0.45

 seja

0.43

_be

0.43

 Ø¨ØªÙĪØ§ÙĨ

0.42

.be

0.40

Activations Density 0.241%

references to legal and governmental frameworks

No Comments

No Known Activations