INDEX

Explanations

brand names and company mentions in 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

agen

-0.16

Parms

-0.14

inz

-0.14

 ÑģÐ¾Ð¼

-0.14

fm

-0.14

Formats

-0.14

 Geld

-0.13

_lite

-0.13

 Mana

-0.13

 ITER

-0.13

POSITIVE LOGITS

igon

0.18

ysl

0.17

 ****************************************************************************

0.15

 reuse

0.14

ully

0.14

ojis

0.14

iface

0.13

 refresh

0.13

NDER

0.13

antee

0.13

Activations Density 0.040%

brand names and company mentions in the text

No Comments

No Known Activations