INDEX

Explanations

words related to various forms of 'ul' and 'sul' suffixes, which often denote specific conditions or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

elli

-0.19

lint

-0.18

ese

-0.17

ÐµÐ½Ñģ

-0.17

ey

-0.16

tal

-0.16

ecal

-0.16

epar

-0.16

emer

-0.16

eg

-0.16

POSITIVE LOGITS

trasound

0.25

monary

0.22

ski

0.21

icrous

0.21

terior

0.20

iflower

0.20

tras

0.20

OCK

0.20

led

0.19

áº·ng

0.19

Activations Density 0.035%

words related to various forms of 'ul' and 'sul' suffixes, which often denote specific conditions or concepts

No Comments

No Known Activations