INDEX

Explanations

technical terms and concepts related to scientific analysis and applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

heid

-0.18

iteit

-0.16

uvre

-0.16

udio

-0.15

rophe

-0.15

avad

-0.15

ifice

-0.15

çĪ½

-0.15

iÃ³n

-0.15

ate

-0.14

POSITIVE LOGITS

ations

0.41

itions

0.40

uations

0.39

izations

0.38

ulations

0.37

iations

0.37

ifications

0.36

isations

0.36

utions

0.36

isions

0.35

Activations Density 0.290%

technical terms and concepts related to scientific analysis and applications

No Comments

No Known Activations