INDEX

Explanations

terms related to employee rights and agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

rait

-0.15

 whatever

-0.13

 laughter

-0.13

whatever

-0.13

raw

-0.13

Whatever

-0.13

ÙĪÙħ

-0.13

cps

-0.13

iten

-0.13

bole

-0.13

POSITIVE LOGITS

 Powers

0.26

 powers

0.24

powers

0.23

 duties

0.21

 certain

0.21

Dut

0.20

 effect

0.20

 Contents

0.20

Scope

0.19

 Effect

0.18

Activations Density 0.032%

terms related to employee rights and agreements

No Comments

No Known Activations