INDEX

Explanations

technical terms and concepts related to algorithms, specifically sorting and merging data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

³

-0.17

ent

-0.16

iage

-0.15

 pure

-0.15

 basket

-0.15

bled

-0.15

Ãģ

-0.15

 dere

-0.15

itzer

-0.14

lesi

-0.14

POSITIVE LOGITS

_UNS

0.16

Å¡ov

0.16

 vbCrLf

0.14

Ctrls

0.14

DataExchange

0.14

íĥģ

0.14

imity

0.14

PixelFormat

0.14

Ð²Ð¾Ð»Ñı

0.13

Activations Density 0.093%

technical terms and concepts related to algorithms, specifically sorting and merging data structures

No Comments

No Known Activations