INDEX

Explanations

references to specific establishments or organizational milestones

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

onium

-0.16

Glo

-0.16

ForMember

-0.15

 Blasio

-0.14

lama

-0.14

SizeMode

-0.14

oku

-0.14

 thá»©

-0.14

ungi

-0.14

etros

-0.13

POSITIVE LOGITS

oon

0.14

isco

0.14

ilen

0.14

abil

0.13

omb

0.13

ild

0.13

ada

0.13

 Resolver

0.13

uhn

0.13

Activations Density 0.141%

references to specific establishments or organizational milestones

No Comments

No Known Activations