INDEX

Explanations

abbreviations or acronyms related to organizations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

rine

-0.17

Sas

-0.16

queues

-0.13

 misunder

-0.13

ensely

-0.13

 Sting

-0.13

``(

-0.13

oloj

-0.13

leen

-0.12

POSITIVE LOGITS

ascar

0.14

krom

0.14

Ð¸ÑĨ

0.14

æ°ı

0.14

ocator

0.14

åĩĢ

0.14

xima

0.14

ASM

0.13

 Äįast

0.13

uts

0.13

Activations Density 0.061%

abbreviations or acronyms related to organizations and entities

No Comments

No Known Activations