INDEX

Explanations

technical terms related to data structures and file management

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

StackSize

-0.18

 STACK

-0.17

Ð¾Ð½ÑĮ

-0.16

mund

-0.15

 Stack

-0.15

STACK

-0.15

NSBundle

-0.15

éĤ¦

-0.15

 Mund

-0.15

taj

-0.15

POSITIVE LOGITS

 compressed

0.17

 Collision

0.17

 bloom

0.17

 compression

0.15

hit

0.15

 Bloom

0.15

 keys

0.15

store

0.15

 Compression

0.15

 store

0.15

Activations Density 0.186%

technical terms related to data structures and file management

No Comments

No Known Activations