INDEX

Explanations

punctuation marks, particularly commas and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

erton

-0.18

fy

-0.15

ngth

-0.15

dur

-0.15

dont

-0.15

rub

-0.14

 similarly

-0.14

Id

-0.14

yle

-0.14

 Carnegie

-0.14

POSITIVE LOGITS

AMA

0.15

Ð°Ð·Ð°

0.15

HeaderValue

0.15

chner

0.14

ela

0.14

áº¯m

0.14

 commercially

0.14

 ÐĴÐ¸ÐºÐ¸

0.14

treeview

0.14

>{!!

0.14

Activations Density 0.022%

punctuation marks, particularly commas and dates

No Comments

No Known Activations