INDEX

Explanations

phrases that indicate relationships and interpersonal dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

utan

-0.16

orsk

-0.16

ÌĨ

-0.15

usz

-0.15

ucky

-0.15

ÏĥÎ¿Ïħ

-0.15

orthy

-0.15

.pitch

-0.14

ongan

-0.14

usses

-0.14

POSITIVE LOGITS

 well

0.61

well

0.51

 Well

0.49

Well

0.46

 WELL

0.44

 bien

0.34

 wells

0.33

"Well

0.30

“Well

0.29

 wellbeing

0.25

Activations Density 0.149%

phrases that indicate relationships and interpersonal dynamics

No Comments

No Known Activations