INDEX

Explanations

instances of loops or iterations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ilities

-0.17

zi

-0.15

artisan

-0.14

_gui

-0.14

 Heap

-0.14

_anchor

-0.14

 pearl

-0.14

íķĳ

-0.14

 duro

-0.14

ubby

-0.14

POSITIVE LOGITS

ardi

0.15

zelf

0.15

bson

0.14

_queryset

0.14

oris

0.14

 kendine

0.14

ocos

0.13

ESS

0.13

oÅ¾

0.13

newInstance

0.13

Activations Density 0.076%

instances of loops or iterations in code

No Comments

No Known Activations