INDEX

Explanations

punctuation marks 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

but

-0.25

but

-0.24

and

-0.24

↵

-0.24

 which

-0.23

and

-0.20

or

-0.20

-0.19

so

-0.18

...↵

-0.18

POSITIVE LOGITS

.scalablytyped

0.19

.ISupportInitialize

0.15

uitka

0.15

otec

0.15

celik

0.14

antics

0.14

@nate

0.14

.updateDynamic

0.14

.variant

0.14

 tÃ©Å¾

0.14

Activations Density 0.387%

punctuation marks in various contexts

No Comments

No Known Activations