INDEX

Explanations

references to image or credit citations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ãĥ³ãĥĲ

-0.15

gregate

-0.15

 Gabri

-0.14

ãĥ¬ãĥĵ

-0.14

ViewInit

-0.14

 Studio

-0.14

eced

-0.14

é¼ł

-0.13

ÑģÑĤÐ²

-0.13

sume

-0.13

POSITIVE LOGITS

/WebAPI

0.15

ëĪ

0.15

ÙĨØ³

0.14

orado

0.14

opal

0.14

 kapit

0.14

OptionsResolver

0.14

 ÐĺÑģ

0.14

 explan

0.13

ingo

0.13

Activations Density 0.005%

references to image or credit citations within the text

No Comments

No Known Activations