INDEX

Explanations

punctuation marks, specifically commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

isma

-0.20

ISK

-0.19

uess

-0.17

isk

-0.16

iday

-0.15

stru

-0.15

ROME

-0.14

eron

-0.14

ILA

-0.14

zik

-0.14

POSITIVE LOGITS

erset

0.15

com

0.15

ackbar

0.15

SEP

0.14

kees

0.14

Kur

0.14

 ç´

0.14

BuilderInterface

0.13

.EventQueue

0.13

Activations Density 0.000%

punctuation marks, specifically commas

No Comments

No Known Activations