INDEX

Explanations

terms related to calibration and standards in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

gni

-0.16

assa

-0.15

spir

-0.14

Schedulers

-0.14

ÙĦÛĮØ³ÛĮ

-0.14

adel

-0.14

æ¦

-0.14

à¸±à¸įà¸į

-0.14

 Kaplan

-0.13

hower

-0.13

POSITIVE LOGITS

 standards

0.39

 reference

0.36

cal

0.35

 calibration

0.35

 Standards

0.35

 Reference

0.32

reference

0.31

Reference

0.30

 Calibration

0.29

 references

0.28

Activations Density 0.047%

terms related to calibration and standards in technical contexts

No Comments

No Known Activations