INDEX

Explanations

mathematical expressions and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ingen

-0.14

.newArrayList

-0.13

\xc

-0.13

emes

-0.12

ictured

-0.12

inha

-0.12

eteor

-0.12

æĮ¯ãĤĬ

-0.12

Ð¾Ð·Ð²

-0.12

"math

-0.11

POSITIVE LOGITS

 implies

0.32

 imply

0.31

impl

0.30

 hence

0.28

 whence

0.27

 implying

0.27

 implication

0.25

 impl

0.25

 therefore

0.24

_impl

0.24

Activations Density 0.259%

mathematical expressions and relationships

No Comments

No Known Activations