INDEX

Explanations

locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

al

-0.15

iao

-0.14

 Arbeit

-0.13

rtl

-0.13

 Corp

-0.13

allo

-0.13

ÏĥÏĦÎ¬

-0.13

Rig

-0.13

 frozen

-0.13

 Eins

-0.13

POSITIVE LOGITS

uÄį

0.15

formace

0.15

-valu

0.14

neh

0.14

ycz

0.14

illac

0.14

TestingModule

0.14

ldap

0.14

.bn

0.14

ependency

0.14

Activations Density 0.068%

locations and addresses

No Comments

No Known Activations