INDEX

Explanations

phrases indicating health benefits and wellness topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-UA

-0.15

issy

-0.15

le

-0.14

Ð½Ð°ÑĩÐµ

-0.14

plus

-0.14

 Firstly

-0.14

ÏĥÏĦÎ¿

-0.13

zung

-0.13

 signific

-0.13

POSITIVE LOGITS

 recently

0.21

 lately

0.16

 Recently

0.16

Recently

0.15

oble

0.15

ãģĿãĤĵãģª

0.15

anka

0.15

resa

0.15

oom

0.14

 however

0.14

Activations Density 0.128%

phrases indicating health benefits and wellness topics

No Comments

No Known Activations