INDEX

Explanations

terms related to scientific studies and research objectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 elucid

-0.22

 alloc

-0.16

allocate

-0.15

arya

-0.14

 Alloc

-0.14

Dub

-0.13

ORT

-0.13

 elabor

-0.13

/respond

-0.13

 fluct

-0.13

POSITIVE LOGITS

 study

0.47

 studying

0.46

study

0.39

 investigate

0.36

 Study

0.36

 understanding

0.36

 studies

0.34

Study

0.34

stud

0.34

 investigating

0.34

Activations Density 0.308%

terms related to scientific studies and research objectives

No Comments

No Known Activations