INDEX

Explanations

references to educational institutions and graduation experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

anst

-0.17

oth

-0.16

utes

-0.16

ellan

-0.15

tml

-0.15

izens

-0.15

appen

-0.15

yscale

-0.15

isma

-0.14

Leo

-0.14

POSITIVE LOGITS

Jeh

0.16

Cab

0.16

Benefits

0.15

cab

0.15

 onData

0.14

bell

0.14

pei

0.14

.assertThat

0.14

ppelin

0.14

ighter

0.14

Activations Density 0.056%

references to educational institutions and graduation experiences

No Comments

No Known Activations