INDEX

Explanations

the word "that."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

rer

-0.16

abis

-0.15

 ones

-0.15

adj

-0.15

adu

-0.14

UX

-0.14

uito

-0.14

vor

-0.14

ÐºÐ»Ð°Ð´

-0.13

mÃ®

-0.13

POSITIVE LOGITS

ancement

0.15

éº

0.15

unsch

0.14

we

0.14

 exists

0.14

ohn

0.14

_NC

0.13

hiro

0.13

we

0.13

Greetings

0.13

Activations Density 0.140%

the word "that."

No Comments

No Known Activations