INDEX

Explanations

programming and class collection-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ovel

-0.15

loys

-0.15

aber

-0.14

uria

-0.14

ustos

-0.14

acen

-0.14

æĺİ

-0.13

ļĮ

-0.13

 neutral

-0.13

artner

-0.13

POSITIVE LOGITS

.newArrayList

0.21

 Lists

0.17

Lists

0.17

lists

0.16

Collections

0.16

_Api

0.16

 lists

0.15

ange

0.15

 Sets

0.14

.ExecuteReader

0.14

Activations Density 0.013%

programming and class collection-related terms

No Comments

No Known Activations