INDEX

Explanations

keywords related to programming and 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

rant

-0.16

-0.15

ritt

-0.15

éŁ³

-0.14

 Gand

-0.14

 Cabinets

-0.14

chem

-0.14

æľĭ

-0.13

 GRAT

-0.13

moz

-0.13

POSITIVE LOGITS

å¾¡

0.14

du

0.14

.MixedReality

0.14

 blanks

0.14

æ´

0.14

ungeons

0.14

lobals

0.14

ľĺ

0.14

Smy

0.14

/YYYY

0.14

Activations Density 0.032%

keywords related to programming and data structures

No Comments

No Known Activations