INDEX

Explanations

technical terms related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

eneg

-0.18

-0.17

lsru

-0.15

 Stevenson

-0.15

ikh

-0.15

arra

-0.14

ANCELED

-0.14

qu

-0.13

ypad

-0.13

abar

-0.13

POSITIVE LOGITS

iad

0.15

IDA

0.14

cheng

0.14

chest

0.14

letes

0.14

à¹ĥà¸Ī

0.14

adir

0.14

Î¹Î´

0.14

.ns

0.14

apt

0.13

Activations Density 0.011%

technical terms related to programming and software development

No Comments

No Known Activations