INDEX

Explanations

terms related to data structures and algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Enc

-0.15

irie

-0.15

Enc

-0.15

-vars

-0.15

Klo

-0.15

hydration

-0.15

ame

-0.14

 recurse

-0.14

enc

-0.14

éº

-0.14

POSITIVE LOGITS

 queue

0.29

 Queue

0.26

deque

0.25

queue

0.24

Queue

0.24

(queue

0.24

 deque

0.24

 stack

0.24

Que

0.23

Deque

0.23

Activations Density 0.162%

terms related to data structures and algorithms

No Comments

No Known Activations