INDEX

Explanations

phrases or concepts that express action or engagement

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

esome

-0.15

acie

-0.15

cales

-0.15

esian

-0.14

 ÙħÙħ

-0.14

coma

-0.14

 Nested

-0.14

chine

-0.14

ustr

-0.14

ucket

-0.14

POSITIVE LOGITS

engo

0.15

.RichTextBox

0.14

 ÄĳÃ³

0.14

iltr

0.14

ResultsController

0.13

actus

0.13

ÏģÎ¯ÏĤ

0.13

 Wikispecies

0.13

 wÅĤ

0.13

 èĭ±

0.13

Activations Density 0.025%

phrases or concepts that express action or engagement

No Comments

No Known Activations