INDEX

Explanations

references to academic or professional credentials and affiliations

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

bid

-0.19

ase

-0.16

her

-0.15

 Cors

-0.15

aro

-0.15

an

-0.15

oni

-0.14

he

-0.14

on

-0.14

arp

-0.14

POSITIVE LOGITS

iyet

0.15

ONGL

0.15

 Redistributions

0.15

.MouseAdapter

0.15

Ø¡

0.14

Fcn

0.14

à¤¤à¤®

0.14

ystack

0.14

eyer

0.14

azu

0.14

Activations Density 0.005%

references to academic or professional credentials and affiliations

No Comments

No Known Activations