INDEX

Explanations

verbs and their related forms, particularly focusing on processes related to classification and management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÃŃ

-0.18

ingu

-0.15

Ð¾Ð±ÑĢÐ°Ð·

-0.15

achu

-0.15

Ã©s

-0.14

own

-0.14

itter

-0.14

utin

-0.13

ach

-0.13

heet

-0.13

POSITIVE LOGITS

naire

0.28

naires

0.22

ally

0.21

ist

0.20

ary

0.20

al

0.19

ists

0.19

nel

0.18

nal

0.18

ALLY

0.18

Activations Density 1.323%

verbs and their related forms, particularly focusing on processes related to classification and management

No Comments

No Known Activations