INDEX

Explanations

references to locations and their attributes 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 orth

-0.14

Vac

-0.14

 Reference

-0.14

 precaution

-0.14

rames

-0.14

Sar

-0.13

eer

-0.13

(_,

-0.13

ording

-0.13

ãĢ

-0.13

POSITIVE LOGITS

 =================================================================================

0.16

zk

0.16

artz

0.15

untu

0.15

AndUpdate

0.15

IODevice

0.14

croft

0.14

 IonicModule

0.14

asin

0.14

zin

0.14

Activations Density 0.253%

references to locations and their attributes or events

No Comments

No Known Activations