INDEX

Explanations

references to official documents or memorandums

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

elman

-0.15

ccion

-0.14

Hom

-0.14

umba

-0.14

 Nations

-0.14

ustr

-0.14

hou

-0.13

áº±m

-0.13

usting

-0.13

-volume

-0.13

POSITIVE LOGITS

ural

0.15

alt

0.15

orex

0.14

osy

0.14

udev

0.14

Tar

0.14

.quick

0.13

ÄĽn

0.13

à¸ŀà¸¢

0.13

 Bison

0.13

Activations Density 0.004%

references to official documents or memorandums

No Comments

No Known Activations