INDEX

Explanations

terms related to children and children-oriented products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

yntax

-0.16

éłĨ

-0.15

nyder

-0.14

woff

-0.14

rray

-0.14

DAQ

-0.14

/goto

-0.14

Å¾e

-0.14

ãĥĲãĤ¹

-0.13

reater

-0.13

POSITIVE LOGITS

bos

0.14

naments

0.14

aph

0.14

 errorThrown

0.14

 Owens

0.14

 respectively

0.14

pard

0.13

Ø§Ø®

0.13

Bos

0.13

pad

0.13

Activations Density 0.256%

terms related to children and children-oriented products

No Comments

No Known Activations