INDEX

Explanations

technical jargon or abbreviations related to programming and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

à¤°

-0.19

rms

-0.19

-0.17

rani

-0.16

rint

-0.16

ront

-0.15

rne

-0.15

rar

-0.15

rlen

-0.15

RI

-0.15

POSITIVE LOGITS

yre

0.29

ech

0.27

ucky

0.26

ertainment

0.25

ing

0.23

astic

0.22

ropy

0.21

een

0.21

egral

0.21

Activations Density 0.074%

technical jargon or abbreviations related to programming and technology

No Comments

No Known Activations