INDEX

Explanations

phrases related to conditionals and hypotheticals in discussions

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

 scatter

-0.13

bow

-0.13

urry

-0.13

shopping

-0.13

alk

-0.13

 Petite

-0.13

 ãĤ»

-0.13

-0.12

Ash

-0.12

POSITIVE LOGITS

ibase

0.15

amerate

0.15

ickerView

0.14

otton

0.14

ÏĮÎ³

0.14

oreach

0.14

legate

0.14

cÃŃ

0.14

.opensource

0.14

NotFoundError

0.14

Activations Density 0.173%

phrases related to conditionals and hypotheticals in discussions

No Comments

No Known Activations