INDEX

Explanations

phrases and words indicating additional value or bonus aspects

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

atsapp

-0.18

nya

-0.17

stone

-0.16

spot

-0.16

te

-0.16

alytics

-0.16

tech

-0.16

modo

-0.15

go

-0.15

ston

-0.15

POSITIVE LOGITS

ordinary

0.49

ordin

0.40

ord

0.39

-large

0.35

ORD

0.32

-special

0.29

ordinal

0.29

Ord

0.28

-cur

0.28

 ordinary

0.27

Activations Density 0.023%

phrases and words indicating additional value or bonus aspects

No Comments

No Known Activations