INDEX

Explanations

references to the character or entity "Per."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

wargs

-0.18

adder

-0.17

ercul

-0.16

ften

-0.15

plain

-0.14

 jenter

-0.14

aight

-0.14

sdale

-0.14

ersh

-0.14

auty

-0.14

POSITIVE LOGITS

uvian

0.21

vez

0.17

ugin

0.17

seo

0.16

icles

0.16

reira

0.16

ROT

0.16

kins

0.16

ennial

0.15

utz

0.15

Activations Density 0.018%

references to the character or entity "Per."

No Comments

No Known Activations