INDEX

Explanations

mathematical symbols and expressions related to inequalities and proofs

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

eam

-0.16

reff

-0.15

emailer

-0.14

.yang

-0.14

SCALL

-0.14

æĤł

-0.14

æµİ

-0.14

ãĤ¤ãĤ¯

-0.14

,↵

-0.14

.,↵

-0.14

POSITIVE LOGITS

color

0.29

 color

0.28

space

0.24

large

0.24

Large

0.23

impl

0.23

 Color

0.23

gt

0.22

tag

0.22

lt

0.22

Activations Density 0.186%

mathematical symbols and expressions related to inequalities and proofs

No Comments

No Known Activations