INDEX

Explanations

technical discussions related to programming and APIs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Cinder

-0.16

WN

-0.14

.mybatisplus

-0.14

é©

-0.14

unset

-0.14

\application

-0.14

ccb

-0.14

.autoconfigure

-0.14

ï»¿#

-0.13

/cpp

-0.13

POSITIVE LOGITS

 Observable

0.49

 observable

0.47

Observable

0.44

 Observ

0.42

 observ

0.42

observable

0.42

Observ

0.37

observ

0.35

Obs

0.33

.Observable

0.33

Activations Density 0.014%

technical discussions related to programming and APIs

No Comments

No Known Activations