INDEX

Explanations

punctuation marks, particularly colons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ãłng

-0.15

auge

-0.14

ãĤ¢ãĥ³

-0.14

isspace

-0.14

 ìĤ¼

-0.14

anton

-0.14

Ø§ØµÙĦ

-0.14

ÐµÐ²Ð°

-0.14

ekim

-0.13

ä»£

-0.13

POSITIVE LOGITS

().'/

0.16

usch

0.15

Bid

0.15

igrations

0.15

ãĥ³ãĥķ

0.15

Fx

0.14

bus

0.14

cy

0.14

ÑıÐ¶

0.14

 Quote

0.14

Activations Density 0.021%

punctuation marks, particularly colons

No Comments

No Known Activations