INDEX

Explanations

phrases that convey significant historical figures or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

/is

-0.21

ãĥ¥

-0.15

ificate

-0.14

arrings

-0.14

 created

-0.14

ateria

-0.14

usat

-0.14

nt

-0.14

 initially

-0.14

 like

-0.14

POSITIVE LOGITS

 today

0.24

 believed

0.24

 said

0.23

 credited

0.23

today

0.22

now

0.22

said

0.21

ä»Ĭå¤©

0.21

 remembered

0.21

 heute

0.21

Activations Density 0.214%

phrases that convey significant historical figures or events

No Comments

No Known Activations