INDEX

Explanations

references to updates and the status of various entities and information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

apat

-0.15

alker

-0.15

iek

-0.15

untu

-0.15

vester

-0.15

iface

-0.15

VIS

-0.14

_LS

-0.14

 $('#'

-0.14

athers

-0.14

POSITIVE LOGITS

burg

0.21

 Engineering

0.17

engine

0.17

 engine

0.17

eci

0.16

 Engine

0.16

 Commission

0.16

 ENGINE

0.16

berg

0.15

ret

0.15

Activations Density 0.024%

references to updates and the status of various entities and information

No Comments

No Known Activations