INDEX

Explanations

parentheses or similar punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ãĥªãĥ¼ãĤº

-0.17

-0.16

ify

-0.14

auc

-0.14

Äħd

-0.14

 ...(

-0.14

olumn

-0.14

UpInside

-0.13

ow

-0.13

POSITIVE LOGITS

umps

0.16

'gc

0.15

Â±

0.15

aka

0.15

-navbar

0.13

|_

0.13

ward

0.13

ë³µ

0.13

à¸¢à¸ģ

0.13

ills

0.12

Activations Density 0.447%

parentheses or similar punctuation marks

No Comments

No Known Activations