INDEX

Explanations

specific years and dates mentioned in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

LineColor

-0.15

WithMany

-0.15

endregion

-0.15

][/

-0.14

errals

-0.14

emiah

-0.14

Advertisements

-0.14

#endregion

-0.14

 offline

-0.14

POSITIVE LOGITS

</

0.16

æº

0.15

ura

0.14

cott

0.14

edis

0.14

ohon

0.14

ioni

0.14

 Owen

0.14

isto

0.14

nore

0.14

Activations Density 0.045%

specific years and dates mentioned in a text

No Comments

No Known Activations