INDEX

Explanations

technical terminology 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Aw

-0.15

Î´ÏĮÎ½

-0.15

 mList

-0.14

adge

-0.14

éĿ©

-0.14

rol

-0.14

vek

-0.14

ØºÙĦ

-0.14

********************************************************************************

-0.14

icos

-0.14

POSITIVE LOGITS

inned

0.15

apel

0.15

innamon

0.14

eness

0.14

amic

0.14

riter

0.14

ocr

0.14

sur

0.14

lav

0.14

Activations Density 0.013%

technical terminology related to programming and data structures

No Comments

No Known Activations