INDEX

Explanations

references to specific technology products and versions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

à¸£à¸ĵ

-0.16

arness

-0.16

$MESS

-0.15

 UÅ¾

-0.15

isode

-0.15

Ð±Ð¸ÑĤ

-0.15

.DropDown

-0.15

 hÃ£

-0.15

 serialVersionUID

-0.15

ä¼

-0.15

POSITIVE LOGITS

lap

0.16

rim

0.16

into

0.15

inspace

0.15

sil

0.15

 blow

0.14

fil

0.14

common

0.14

Wa

0.14

Activations Density 0.009%

references to specific technology products and versions

No Comments

No Known Activations