INDEX

Explanations

phrases and expressions that describe dynamic interactions or mixed relationships in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

SupportedContent

-0.15

Ã´i

-0.14

etu

-0.14

etik

-0.13

 ******************************************************************************↵

-0.13

cheid

-0.13

 hoÃ¡

-0.13

 diyor

-0.13

iliated

-0.13

RuntimeObject

-0.13

POSITIVE LOGITS

-of

0.23

-with

0.19

-from

0.17

-is

0.16

ashtra

0.16

-to

0.15

-in

0.15

Looper

0.15

/or

0.15

-and

0.14

Activations Density 0.162%

phrases and expressions that describe dynamic interactions or mixed relationships in various contexts

No Comments

No Known Activations