INDEX

Explanations

words related to combining or integration processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

contre

-0.16

icrous

-0.15

 Pace

-0.15

ceu

-0.15

ORED

-0.15

uppe

-0.15

lopen

-0.15

åĲ¾

-0.15

 incumb

-0.15

ompiler

-0.15

POSITIVE LOGITS

ining

0.30

inator

0.29

ination

0.24

obox

0.23

ative

0.23

usted

0.23

ust

0.23

ines

0.22

inations

0.21

iners

0.21

Activations Density 0.004%

words related to combining or integration processes

No Comments

No Known Activations