INDEX

Explanations

recurring numerical values associated with durations or timeframes

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

TestFixture

-0.17

lesi

-0.17

led

-0.17

Case

-0.17

jÅ¡ÃŃ

-0.17

ime

-0.16

pace

-0.16

odos

-0.16

stakes

-0.16

 hundred

-0.15

POSITIVE LOGITS

 Downing

0.33

acious

0.28

ured

0.27

acity

0.26

URED

0.20

agers

0.20

anted

0.18

ets

0.18

ylon

0.18

.UnitTesting

0.17

Activations Density 0.096%

recurring numerical values associated with durations or timeframes

No Comments

No Known Activations