INDEX

Explanations

programming-related code snippets and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

pector

-0.16

 Abbott

-0.15

igid

-0.15

lator

-0.15

ombies

-0.15

ÑİÑĢ

-0.15

otland

-0.14

 Fallon

-0.14

nish

-0.14

_EDITOR

-0.14

POSITIVE LOGITS

odd

0.19

 ListItem

0.18

ForRow

0.18

pl

0.18

twe

0.17

 item

0.16

vore

0.15

UITableViewCell

0.15

 cell

0.15

ListItem

0.15

Activations Density 0.088%

programming-related code snippets and structures

No Comments

No Known Activations