INDEX

Explanations

action verbs and linking verbs within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Bris

-0.17

ï»¿#

-0.17

mond

-0.17

itra

-0.16

Ø³ØªÙĩ

-0.14

anou

-0.14

anik

-0.14

Î²Î¬

-0.14

 znam

-0.14

ree

-0.14

POSITIVE LOGITS

atan

0.17

ToFit

0.16

ungan

0.15

PRI

0.15

EFR

0.14

 cause

0.14

ial

0.14

ismet

0.14

ohan

0.14

udies

0.14

Activations Density 0.000%

action verbs and linking verbs within the text

No Comments

No Known Activations