INDEX

Explanations

patterns in code structure and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

wyn

-0.17

ogne

-0.16

aday

-0.15

andre

-0.15

exc

-0.15

-0.14

 stoi

-0.14

Ð»Ð¸Ðº

-0.14

åľŃ

-0.14

uster

-0.14

POSITIVE LOGITS

 static

0.18

 Ð´ÑĥÑħ

0.16

emand

0.16

bsolute

0.16

 STRICT

0.15

OVE

0.15

.enum

0.15

ouver

0.15

ablish

0.14

overe

0.14

Activations Density 0.080%

patterns in code structure and syntax elements

No Comments

No Known Activations