INDEX

Explanations

geographical directions and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

idth

-0.16

ustomed

-0.15

=sub

-0.14

akens

-0.14

	explicit

-0.14

 stag

-0.14

akedown

-0.14

POSITIVE LOGITS

 portion

0.24

 portions

0.19

 part

0.18

ward

0.18

end

0.18

 side

0.18

 aspect

0.17

side

0.17

CDATA

0.17

wards

0.17

Activations Density 0.038%

geographical directions and locations

No Comments

No Known Activations