INDEX

Explanations

numerical representations, particularly focusing on times and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ãĥ³ãĤ¸

-0.16

ansen

-0.16

ESCO

-0.16

entai

-0.15

Ð»Ð°Ð¶

-0.15

AZE

-0.14

addock

-0.14

bigint

-0.14

ãĥ³ãĤ¬

-0.14

kil

-0.14

POSITIVE LOGITS

PM

0.35

PM

0.33

pm

0.30

pm

0.28

.pm

0.26

_pm

0.26

_PM

0.24

(pm

0.22

pm

0.20

Activations Density 0.019%

numerical representations, particularly focusing on times and dates

No Comments

No Known Activations