INDEX

Explanations

technical terms and concepts related to formal definitions, content structures, and event management in programming or data processing

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.15

heimer

-0.14

éŃĤ

-0.14

ulty

-0.14

 Genuine

-0.14

reu

-0.14

éļĶ

-0.14

oram

-0.14

itol

-0.14

POSITIVE LOGITS

patial

0.16

hest

0.15

abox

0.15

Äĥng

0.15

 Pickup

0.14

 Conditioning

0.14

 pháº©m

0.14

ignet

0.14

ħį

0.14

gratis

0.13

Activations Density 0.006%

technical terms and concepts related to formal definitions, content structures, and event management in programming or data processing

No Known Activations